Facial-Recognisation-With-siamese-Network.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "18b6580d-6a30-4cd5-8e39-aee1263a4d51",
   "metadata": {},
   "source": [
    "## Installing all our relevant dependencies \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "525d35e4-d5e4-480b-8f43-8a3c107f2bcd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: tensorflow in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (2.16.1)\n",
      "Requirement already satisfied: opencv-python in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (4.9.0.80)\n",
      "Requirement already satisfied: matplotlib in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (3.8.4)\n",
      "Requirement already satisfied: tensorflow-intel==2.16.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow) (2.16.1)\n",
      "Requirement already satisfied: absl-py>=1.0.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (2.1.0)\n",
      "Requirement already satisfied: astunparse>=1.6.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.6.3)\n",
      "Requirement already satisfied: flatbuffers>=23.5.26 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (24.3.25)\n",
      "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (0.5.4)\n",
      "Requirement already satisfied: google-pasta>=0.1.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (0.2.0)\n",
      "Requirement already satisfied: h5py>=3.10.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (3.11.0)\n",
      "Requirement already satisfied: libclang>=13.0.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (18.1.1)\n",
      "Requirement already satisfied: ml-dtypes~=0.3.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (0.3.2)\n",
      "Requirement already satisfied: opt-einsum>=2.3.2 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (3.3.0)\n",
      "Requirement already satisfied: packaging in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (23.2)\n",
      "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (4.25.3)\n",
      "Requirement already satisfied: requests<3,>=2.21.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (2.31.0)\n",
      "Requirement already satisfied: setuptools in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (57.4.0)\n",
      "Requirement already satisfied: six>=1.12.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.16.0)\n",
      "Requirement already satisfied: termcolor>=1.1.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (2.4.0)\n",
      "Requirement already satisfied: typing-extensions>=3.6.6 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (4.11.0)\n",
      "Requirement already satisfied: wrapt>=1.11.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.16.0)\n",
      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.62.1)\n",
      "Requirement already satisfied: tensorboard<2.17,>=2.16 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (2.16.2)\n",
      "Requirement already satisfied: keras>=3.0.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (3.2.1)\n",
      "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (0.31.0)\n",
      "Requirement already satisfied: numpy<2.0.0,>=1.23.5 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.26.4)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from matplotlib) (1.2.1)\n",
      "Requirement already satisfied: cycler>=0.10 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from matplotlib) (0.12.1)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from matplotlib) (4.51.0)\n",
      "Requirement already satisfied: kiwisolver>=1.3.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from matplotlib) (1.4.5)\n",
      "Requirement already satisfied: pillow>=8 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from matplotlib) (10.3.0)\n",
      "Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from matplotlib) (3.1.2)\n",
      "Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from matplotlib) (2.8.2)\n",
      "Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from astunparse>=1.6.0->tensorflow-intel==2.16.1->tensorflow) (0.43.0)\n",
      "Requirement already satisfied: rich in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from keras>=3.0.0->tensorflow-intel==2.16.1->tensorflow) (13.7.1)\n",
      "Requirement already satisfied: namex in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from keras>=3.0.0->tensorflow-intel==2.16.1->tensorflow) (0.0.8)\n",
      "Requirement already satisfied: optree in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from keras>=3.0.0->tensorflow-intel==2.16.1->tensorflow) (0.11.0)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.16.1->tensorflow) (3.3.2)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.16.1->tensorflow) (3.7)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.16.1->tensorflow) (2.2.1)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.16.1->tensorflow) (2024.2.2)\n",
      "Requirement already satisfied: markdown>=2.6.8 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorboard<2.17,>=2.16->tensorflow-intel==2.16.1->tensorflow) (3.6)\n",
      "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorboard<2.17,>=2.16->tensorflow-intel==2.16.1->tensorflow) (0.7.2)\n",
      "Requirement already satisfied: werkzeug>=1.0.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from tensorboard<2.17,>=2.16->tensorflow-intel==2.16.1->tensorflow) (3.0.2)\n",
      "Requirement already satisfied: MarkupSafe>=2.1.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from werkzeug>=1.0.1->tensorboard<2.17,>=2.16->tensorflow-intel==2.16.1->tensorflow) (2.1.5)\n",
      "Requirement already satisfied: markdown-it-py>=2.2.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from rich->keras>=3.0.0->tensorflow-intel==2.16.1->tensorflow) (3.0.0)\n",
      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from rich->keras>=3.0.0->tensorflow-intel==2.16.1->tensorflow) (2.17.2)\n",
      "Requirement already satisfied: mdurl~=0.1 in c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages (from markdown-it-py>=2.2.0->rich->keras>=3.0.0->tensorflow-intel==2.16.1->tensorflow) (0.1.2)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "pip install tensorflow opencv-python matplotlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ab66ce0e-66a1-45f4-9146-6d31f6c3358e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing standard dependencies\n",
    "import cv2\n",
    "import os\n",
    "import random\n",
    "import numpy as np\n",
    "from matplotlib import pyplot as plt\n",
    "\n",
    "# importing deep learning related dependencies-Functional API\n",
    "from tensorflow.keras.models import Model  \n",
    "from tensorflow.keras.layers import Layer,Conv2D,Dense,MaxPooling2D,Input,Flatten \n",
    "\n",
    "import tensorflow as tf\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "488a45df-692c-4564-8f7b-1bb203b34c75",
   "metadata": {},
   "source": [
    "### Creating the Folder Structure "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "1b77416c-ed91-454c-84eb-347e6907e289",
   "metadata": {},
   "outputs": [],
   "source": [
    "# setup paths \n",
    "POS_PATH=os.path.join('data','positive')\n",
    "NEG_PATH=os.path.join('data','negative')\n",
    "ANC_PATH=os.path.join('data','anchor')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3987a3b3",
   "metadata": {},
   "source": [
    "### Making Directories Corresponsing To Path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b557e871",
   "metadata": {},
   "outputs": [],
   "source": [
    "os.makedirs(POS_PATH)\n",
    "os.makedirs(NEG_PATH)\n",
    "os.makedirs(ANC_PATH)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3942fcc0-7bce-488e-96cc-1b89dcb17d29",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Open the video file\n",
    "cap = cv2.VideoCapture(0)\n",
    "\n",
    "# Check if the video file is opened successfully\n",
    "if not cap.isOpened():\n",
    "    print(\"Error: Could not open video file.\")\n",
    "    exit()\n",
    "\n",
    "while True:\n",
    "    # Read a frame from the video\n",
    "    ret, frame = cap.read()\n",
    "\n",
    "    # Check if frame is read successfully\n",
    "    if not ret:\n",
    "        print(\"Error: Could not read frame.\")\n",
    "        break\n",
    "\n",
    "    # Modify RGB values for each pixel\n",
    "    # For example, let's make the frame grayscale\n",
    "    gray_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)\n",
    "\n",
    "    # Display the modified frame\n",
    "    cv2.imshow('Modified Frame', gray_frame)\n",
    "\n",
    "    # Exit the loop if 'q' is pressed\n",
    "    if cv2.waitKey(1) & 0xFF == ord('q'):\n",
    "        break\n",
    "\n",
    "# Release the video capture object and close all windows\n",
    "cap.release()\n",
    "cv2.destroyAllWindows()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c27db9f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.imshow(frame) # to check weather the frame is captured or not "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "54ea98b5-0841-4f57-8b3b-260c445292a5",
   "metadata": {},
   "source": [
    "### Bringing the Images into the Dimension of 250*250"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d9879a8e-a38b-4ffc-9565-dfe631534d21",
   "metadata": {},
   "outputs": [],
   "source": [
    "cap=cv2.VideoCapture(0)\n",
    "while cap.isOpened():\n",
    "    ret,frame=cap.read()\n",
    "\n",
    "    # cut down the frame to 250*250\n",
    "    frame=frame[120:120+250,200:200+250,:]\n",
    "    \n",
    "    cv2.imshow('Image Collection',frame) \n",
    "    if cv2.waitKey(1) & 0xFF == ord('q'):\n",
    "        break\n",
    "cap.release() \n",
    "cv2.destroyAllWindows()\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3d3d2223",
   "metadata": {},
   "outputs": [],
   "source": [
    "ple.imshow(frame)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "da1d6f88-d89f-48fa-9d54-bb70ff56ea35",
   "metadata": {},
   "outputs": [],
   "source": [
    "# importing the uuid library => to generate unique image names\n",
    "import uuid # uniform unique identifier"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0a066805",
   "metadata": {},
   "source": [
    "### Using Open-Cv For Collecting Images of Different Categories "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "deff141f-68ac-456d-9754-b1824cf4aef5",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "cap=cv2.VideoCapture(0)\n",
    "while cap.isOpened():\n",
    "    ret,frame=cap.read()\n",
    "\n",
    "    # cut down the frame to 250*250\n",
    "    frame=frame[120:120+250,200:200+250,:]\n",
    "\n",
    "\n",
    "    # collect anchors \n",
    "    if cv2.waitKey(1) & 0xFF == ord('a'):\n",
    "        # create the unique name \n",
    "        imgname=os.path.join(ANC_PATH,'{}.jpg'.format(uuid.uuid1()))\n",
    "        # write out that image \n",
    "        cv2.imwrite(imgname,frame)\n",
    "\n",
    "\n",
    "\n",
    "    # collect positive images \n",
    "    if cv2.waitKey(1) & 0xFF==ord('p'):\n",
    "        # create a unique id \n",
    "        imgname=os.path.join(POS_PATH,'{}.jpg'.format(uuid.uuid1()))\n",
    "        #write out that imege\n",
    "        cv2.imwrite(imgname,frame)\n",
    "   \n",
    "    cv2.imshow('Image Collection',frame) \n",
    "    if cv2.waitKey(1) & 0xFF == ord('q'): \n",
    "        break\n",
    "cap.release() \n",
    "cv2.destroyAllWindows()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b1d28165-a9bb-41a7-8ff7-ce6d7eaaa0f5",
   "metadata": {},
   "source": [
    "## Preprocessing Images "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d601f764-f274-4155-b802-69dc7b13e138",
   "metadata": {},
   "source": [
    "### Get Image Directories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "bafd0c53-c7a9-4bbc-95dc-63ec8c388f4d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\n    Here we are creating three different datset or three different pipeline \\n    This is going to grab first 300 images from all the files mentioned \\n'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "anchor=tf.data.Dataset.list_files(ANC_PATH+'\\*jpg').take(300)\n",
    "positive=tf.data.Dataset.list_files(POS_PATH+'\\*jpg').take(300)\n",
    "negative=tf.data.Dataset.list_files(NEG_PATH+'\\*jpg').take(300)\n",
    "'''\n",
    "    Here we are creating three different datset or three different pipeline \n",
    "    This is going to grab first 300 images from all the files mentioned \n",
    "'''"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "76a2a7bc-54f8-492f-910c-6d966bf9b77e",
   "metadata": {},
   "outputs": [],
   "source": [
    "dir_test=anchor.as_numpy_iterator() # we are eventually iterating over the data pipeline "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "27283425-ecaa-4ea9-8dfe-ab811de3d106",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "b'data\\\\anchor\\\\85b147a0-d884-11ee-a8f5-80e82c6f74bc.jpg'\n"
     ]
    }
   ],
   "source": [
    "print(dir_test.next())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "63674ecf-8c6e-484f-9f26-b99bd403dd32",
   "metadata": {},
   "source": [
    "### Pre-Processing -Scale and Resize"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "766cddf4-e1cb-4948-aa06-5472402a58f1",
   "metadata": {},
   "source": [
    "This pre-process function over here actually takes the file from the dataset which is being entered \n",
    "<br />\n",
    "It opens the image decodes it and resize it to the desired size "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "5bf67a5b-036e-47c9-8567-d3365da09510",
   "metadata": {},
   "outputs": [],
   "source": [
    "def preprocess(file_path):\n",
    "    byte_img=tf.io.read_file(file_path)  # read the image from the file path \n",
    "    img=tf.io.decode_jpeg(byte_img) # decode jpeg image # the byte img converted to jpeg\n",
    "\n",
    "    # Pre-Processing steps-resizing the image to be 100x100x3\n",
    "    img=tf.image.resize(img,(100,100))\n",
    "    img=img/255.0\n",
    "    return img\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "6e8a6548-afcc-4d59-a056-22cf3214a5c5",
   "metadata": {},
   "outputs": [],
   "source": [
    "img=preprocess('data\\\\anchor\\\\f8f94e69-d885-11ee-bb4a-80e82c6f74bc.jpg')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "591f2219",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8779412"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "img.numpy().max()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4c484c0",
   "metadata": {},
   "source": [
    "plt.imshow(img)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6fa82254-519a-4f63-b24a-01983fce649e",
   "metadata": {},
   "source": [
    "### Creating a Labelled Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "9e660327-e543-479b-81ff-74322bd1af1e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<tf.Tensor: shape=(), dtype=int32, numpy=1>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tf.ones_like(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "66946b36-471b-4851-898d-70695b53dc58",
   "metadata": {},
   "outputs": [],
   "source": [
    "positives=tf.data.Dataset.zip((anchor,positive,tf.data.Dataset.from_tensor_slices(tf.ones(len(anchor)))))\n",
    "\n",
    "negatives=tf.data.Dataset.zip((anchor,negative,tf.data.Dataset.from_tensor_slices(tf.zeros(len(anchor)))))\n",
    "data=positives.concatenate(negatives) # combining the above two dataset \n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6ecab3f3-b870-480a-83bb-7a600ef4639e",
   "metadata": {},
   "source": [
    "(Zip) => this function over here combines the dataset length wise here it is combining anchor dataset positive dataset and label dataset\n",
    "<br />\n",
    "\n",
    "data.Dataset.from_tensor_slices(tf.ones(len(anchor)) => this is actually creating the new dataset from the tensor's of one's which has a length\n",
    "of the anchor dataset Each element in this dataset represents a label for a positive pair "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bbbea415-94f1-46e6-8d3a-c53cdbd7cd81",
   "metadata": {},
   "source": [
    "### Build Train and Test Partition "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b3f686b5-4b09-409b-815d-462c515913c0",
   "metadata": {},
   "source": [
    "The preprocess_twin function takes three inputs: \n",
    "<br />\n",
    "\n",
    "input_img, validation_img, and label, and applies the preprocess function to each input image. \n",
    "<br />\n",
    "\n",
    "It returns a tuple containing the preprocessed versions of the input and validation images along with the label. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "7811f736-d8de-4f4d-878a-ef2c702149a2",
   "metadata": {},
   "outputs": [],
   "source": [
    "samples=data.as_numpy_iterator()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "1d81269b-e7cb-4d67-bda1-3db656669a38",
   "metadata": {},
   "outputs": [],
   "source": [
    "example=samples.next()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "c459cd6b-d8d5-48cb-abc4-377a10af9f7d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(b'data\\\\anchor\\\\046acd8e-d886-11ee-b7bd-80e82c6f74bc.jpg',\n",
       " b'data\\\\positive\\\\bc4d3f02-d884-11ee-ba3a-80e82c6f74bc.jpg',\n",
       " 1.0)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "example"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1408f03b",
   "metadata": {},
   "source": [
    "### Build Train and Test Partition\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "2fbbb709-b615-46eb-8805-13dc3a524664",
   "metadata": {},
   "outputs": [],
   "source": [
    "def preprocess_twin(input_img,validation_img,label):\n",
    "    return(preprocess(input_img),preprocess(validation_img),label)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "8a5c5b43-4cf6-498b-8076-de93045aaf0a",
   "metadata": {},
   "outputs": [],
   "source": [
    "res=preprocess_twin(*example)  # * is unpacking the value and process it through our function "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cb36ae66",
   "metadata": {},
   "source": [
    "plt.imshow(res[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "00d5a467-7f84-4929-bb65-496f731a4242",
   "metadata": {},
   "outputs": [],
   "source": [
    "# we are going to make the data pipeline over here \n",
    "data=data.map(preprocess_twin)\n",
    "data=data.cache() \n",
    "data=data.shuffle(buffer_size=10000) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "82726587-f7fb-461f-9ba2-80580517dee8",
   "metadata": {},
   "outputs": [],
   "source": [
    "samples=data.as_numpy_iterator()\n",
    "# this would grab the dataset with three columns the first columns contains the value for the anchor image \n",
    "# second one is for the positive "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "ff5ff40a-2485-4b18-9bf5-a7e0d7d5c729",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(samples.next())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "3e5c425d-cce1-45cd-ada6-ff7abd6ddff9",
   "metadata": {},
   "outputs": [],
   "source": [
    "samp=samples.next()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "125ec0cc-a87d-4db8-bb07-8b01c1ebfa38",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x19b4968d8d0>"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAaAAAAGgCAYAAADsNrNZAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8fJSN1AAAACXBIWXMAAA9hAAAPYQGoP6dpAACdO0lEQVR4nO29eZhmV10uuvb4DTV2VXVV9ZjuJJ10RjInTQAV+oCKCpIDokEDeA9HCULgXEYF70Uh6LmP5uCNOFyMcAQRVGYhhxMwmBAydMjQ6aQz9DxUdU3fPO3p/pH4rd/7fqlKGoJfAb/3efp59uq1v73XXmvtvWu/72+9PyfLsswoFAqFQvEfDLffDVAoFArFTyb0BaRQKBSKvkBfQAqFQqHoC/QFpFAoFIq+QF9ACoVCoegL9AWkUCgUir5AX0AKhUKh6Av0BaRQKBSKvkBfQAqFQqHoC/QFpFAoFIq+4If2ArrxxhvNli1bTD6fN5dffrm56667flinUigUCsWPIJwfhhfcP/zDP5jf+I3fMH/xF39hLr/8cnPDDTeYz33uc2bv3r1mcnJyxd+maWqOHTtmhoaGjOM4z3XTFAqFQvFDRpZlplqtmvXr1xvXXeE7J/sh4LLLLsuuvfbabjlJkmz9+vXZ9ddf/4y/PXz4cGaM0X/6T//pP/33I/7v8OHDKz7vn3MKrtPpmF27dpmdO3d2/891XbNz505zxx139OzfbrdNpVLp/svUnFuhUCh+LDA0NLRi/XP+ApqfnzdJkpipqSn4/6mpKTMzM9Oz//XXX29GRka6/zZv3vxcN0mhUCgUfcAzySh9j4J773vfa8rlcvff4cOH+90khUKhUPwHwH+uDzgxMWE8zzOzs7Pw/7Ozs2Z6erpn/1wuZ3K53HPdDIVCoVCscjznX0BhGJqLL77Y3HLLLd3/S9PU3HLLLWbHjh3P9ekUCoVC8SOK5/wLyBhj3vGOd5hrrrnGXHLJJeayyy4zN9xwg6nX6+YNb3jDD+N0CoVCofgRxA/lBfQrv/IrZm5uznzgAx8wMzMz5oILLjBf//rXewITFAqFQvGTix/KQtQfBJVKxYyMjPS7GQqFQqH4AVEul83w8PCy9X2PglMoFArFTyb0BaRQKBSKvkBfQAqFQqHoC/QFpFAoFIq+QF9ACoVCoegL9AWkUCgUir5AX0AKhUKh6Av0BaRQKBSKvkBfQAqFQqHoC/QFpFAoFIq+QF9ACoVCoegL9AWkUCgUir7gh+KG3U/IBLDP7LLqUMn+gn+7UmLZ3vNwt8bL/5j/BFjpxOkzNEqkv+WqHstZ+R89x3mGNnI7VkIq24SNWKlPn/EUJzcgy+Jk/gI7mcvuwcqZiVfGSnPiGa6VMyKvLuvh1QR6FoiOe2a/5pXqv/+Bd+i3mTgP1/FMzuCZ80w3tGz/M83yla5HHjd7FsfSLyCFQqFQ9An6AlIoFApFX6AvIIVCoVD0BT+CGtDKnGp2MgIA7bvSL0+KOndW0Hz4QM9Ek2bybwTaeQVdJzsJ6tmh4wT04yRdXoRIezSG5f+mydyE9u3ZQRZWbiTDWWb7aQ4lyz+QrnMyeKYJtNJ4nUwdnecH0nxW0pqeqY+f9YH5xydx4GfSLk/mhnb4WbCCRnpS+P4HYKVnWU9dRjMZ2szHScyzxjOKycsc91letn4BKRQKhaIv0BeQQqFQKPoCfQEpFAqFoi9YxRpQYJ6efF2B0O8p8++Z8effyvfxMxG/Yl9ebMEaEJyW18KkVDYr1q8EuefJcP+8a4fbyJcnDu7Rj33il2WPus9wKfJae0aKKe8V6k+Gdf9BNCD+7UrH8nrWnCHkWpPe49LfiY4nf0h1z9BR4lgODWzGOsJKIlCPyHgyvX4yf/eucH/36DgrtOkZm8f9uFITeDxO4rgrPp9OBj03JdXLsTwZQfiZ7ggeu+XGMjMrrn98hl8rFAqFQvFDhb6AFAqFQtEXrFoKbnxqk3HdJ6mGJLW0Dn9MdjptKCeZ/ezzPHy/pil+XnquB2VHUBthkIO6jCgHx7Fd5/sB1K2b2gLlbdu2dre3bz8F6k7dMg7lqYk8lIcG7XlcB8/jhyGU5fW5dO3Gc2hf26cx9aFpt6CY1BtQbswv2LpSBeoWDxzD8rHZ7nbzQBXqSktYrjVsO9oxUQrU/ma7A+XAt30RdSKoc32c5pH4uyujujbRULGYIlUXj9siuiLhY4nxYDuXwMG5Vxyy7Y9pkpdbeK3HFhbtOSJsE4fjunSeDCg4/Knj4JwJc/YeaNGcCFeYe3ytTPX5Hs7jKLb3rOvSPUvzwBH1Ds3x3vvBzvE0ptBjh58N1E+JuJfo73TX48em+G3PMwfHxw88UUfLHWKkrPJ5fBa02/b+8GiuuT2Daa83irENgYfPtiS1540jHOcgwLFyaD4l0dOvf8jSxFSX9phngn4BKRQKhaIv0BeQQqFQKPoCfQEpFAqFoi9YtRpQFAmaVvCbrotcZ4e4XdezHGWcUIgzaSgZXb7nCR4+Id7XxX2l5UyaYd3R40ehXG/Vu9uLpSWoa7bPhHKjgZrQuqnh7nYYIj87PDwI5cCX/D6FU6bYT77QVHKDyDWneeSIzVABzzs+0t2OqjWoW7tlM5QbZavzdOYqVIe/nT18ortdJ22pMrsA5XoF9aOkYa83oVndIk0oFDpCm+aIIQ0ii219AadPTyhys0djtMeKSJvpEGUf1JvdbT+H/R+4eOJcbsCeM8J+Yi0gIl0hFfPW9/n2xzb6woIpirEuo6UGUvbxqA8T+i3rk4nQQjLDehHOTVforUmGczom8cwV/ZZSSHCP/kvrCeRzxiO9qBPRM8e1v/UD6lOSMqVm16N30dglhsu2za5DumZGuqf4qePxvtioSDxDWVuKKJLaIy1WHls+I7P02dn96BeQQqFQKPoCfQEpFAqFoi/QF5BCoVAo+oJVqwH5Qa67DigT9i7tdhP2C4kvT0VMO3PcSQ9HjOVGw2o1AwNDUBdFuFYmn7e6SKeDbXJ95D9LFVtuPI5rOpaq+NszTsN1QtvPsGuIJsfxesbHsP1DA7ZN+RD/tsgX8bd+autj5nldXE/h+FjOPHs9YQ51qIRI4+K4vd7ietRthkibGTvbXntWw37qlFHriCqoHy3NW22tRuuLmlVcx9Ss2XKzgW0o13A8jODaYyL0W6Rt1GhNTlvsn9C6Mp/WePh5oYPkUHPL0XlKQoPIanitEXHvHs1xkG4ozUZK19dsir4gfYvX1Ml1WEmCbeA1Q80mjocvfsv3bEYar+/bfuS55vm0lkfqIAleW6ONbcgP4HjI1AKdDrYhZcsioX20ac2NS7oaSCikIQY+r7HBNgbix1Ebn0e+z+uPxNpJ0pYcshLKB7bcoXVALt37CWlNaWrvU9eoBqRQKBSKHxHoC0ihUCgUfcGqpeDanbZx/j1UUoRbcuhis4VUDFZTuCd9hiccmiw+RZOEPnHJkqLVtnQdU3lMYclI35TCJw8LqxpjjFmi8OKDR6y1zRlb1kPdlk3roLxhem13e83oANQNI6Nl8iKmOCjgp3/s4s4eu/+K8fBpPAz1RU5STXnsQ6YyvFFLqTgUYhu0kI5IOtjGsGHrJ5pIo8V1thayY9up4DjHbTxvo2HPU2rgcaq1OpRbDTyWDHdtUbi3XyDLpQE7XuUW0hxxCc8z0rLtWKyUoK7ZZAdistcRY8BUmU+hybLFIdNDCS9/kHwXhS3zWBEll4i+iYkPZhfxTmTHVi65MMaYOMHzJGJ+cSj1AFFuEVv+iMtLV7DhMsaAO3a7hXOkQNSrvByPninNBvVTsHw/BT7StNJOxxhjCmJ+dYjq5vGRfc52X2wX5NIcCUTYOc6JZ+eOrl9ACoVCoegL9AWkUCgUir5AX0AKhUKh6AtWrQYU5PyuBhRHImSYQl0HC0UoS03IMcRXss0KcbuSJ2Yr9E6EnGaYk1zpyu9xR/ChEWlWDlnTN0nrOHDUcsoL82jj88Qh1I9O2WA1oY3rKM3D1CCVbZj5QAGnwQDpE0XiywOhlTE/npJW0BFCgkeWRexq73qWi84y5LQDtqfBn5qcmBZpgnMki5Fbl1b7TdKHTILnbYs0BEOLqC0lpNUsLc5DudG02o2fwzkSFPEKPBHKO9qi1A3zeO0bTrNWSJuP4djML+L8eeihx/FYQu8LAtQRFhcx1N0XWmZK95IX4HllpG/G+h1pGZ7HoydDhnFS9OiEmW2Hk/H9jcdNRKhyjLuahOx0uM1SJwnIgymm38ZizoQBh3Pj/RELXTDiMPIc3R8hLZ2Qdkd0Fp6LrZbQi3r6H3/dbNrfcsh26LFeRGHmwoYoEO1N08zgTHx66BeQQqFQKPoCfQEpFAqFoi/QF5BCoVAo+oJVqwE5jtPlI6XFeRJRrD+vZRAaRKeNfKVHogPH2Uu+tsdqhGL2ZTx8RGs8eH1RTuoXvIaA115wFgURo7/QLkFduYGc/ZEZqwlNT05CHa8LOu1Ua3szvgZ1tPVr0YZolH47IPSLgQL2oR/y9YntkPuJ0mWI7YzWHvEaFYf+dkpDkYqd1iBkKe7rpLaNYXEM6uIOakJOs2zbQHPAZDgX4xA1ukJq+2Zs7SjUjYxjORXz2vUotTStzUhE6oB6azvUNVq0DijBfrt/1+7udhRhvxw6hhrWnXfZfct1smAhbSYT1+o6qFlxKhOGI/yBWDnISOeR6RoymgMtWv9VFGurWmRdE9O6GdZFEmEB1CCrLV7HhL8leyNae+iHdixJPu1ZL8VtAusk1mpC7PMosuMTdWisyLZHanKcTr1HJ6d0DJBGXOhoasWjUCgUilUNfQEpFAqFoi9wMv7m6jMqlYoZGRkxw5Ond8OwIdMeWXVEbaShMsh8yG7YZIfis62E/bT26JPWcTiDosi22MObka2HoN1csukxFJLqUUZFeewOWY2E5JosQ0DbRMVwWPnQoA3Lnp5cA3UbprE8NTkK5clxm6V1dIiOS+V83l5vjsK9w5BpNlsOA+zvnr+UiNqAoabslg7RAdLSxJAFS5IgBVdamulun5jZD3Wei8eNOmijNDll6T03wCtoNPE8Q3nbp/kcUqIcr862KxLsDl+tYptGhywtdegoUm7zC+S+nLeh/Lv34LU/8MAjUH7wkSPd7bjDFlhEJRGtJkPUkwz7hY2nPWFBw7ed5+O9JB9tbPHDll7sIi7rmXJrE50nqTI+j0+UeyYzrXL2VAI/ml1BPzp08T0O5CLEvofGzPj5ZMv8LOPjOi7+VlJyMmNAliWmubTPlMtlMzw8bJaDfgEpFAqFoi/QF5BCoVAo+gJ9ASkUCoWiL/iR0IAgjQLZrDgUCit91LOMOGEKlw5CrJfZGDMKHeWQz0SEQXL4ZM5nmxXLy/damJDWwXy/4GB9DhtnayFhnc7DytcKmQ0p5LlAWU6HR1CTWDsx2t1eN4V60cQY8r1ScxgbwbpciNc+WJRaGWlYtG+erkeGt4e0by5HWUIdy1U36hg6Xa8uQLnVKtntRgnqOEsuZ/Os160Vz+Q6TJ2xVELtcmJsurudkB3Q2gm0VZqftdpNjjQfl6xTcoNYnx+28y8fYnh9p433x4H9x7vbjz+OGlCS0NzzR7vb//hPX4O6xx87AWU/wHkQZ3LeYhvcgFIhiPuQw7t52UVOZC1OyWrnmTQhef9wHdvVRMKah0OneV9X6D4xp4Pxl9d/jcHnl/sMj+00sccqFvF+5ueVtEJKyQKL29ShZQqya2SfZWli6ouPqwakUCgUitUJfQEpFAqFoi/QF5BCoVAo+oJVqwGtWXem1YDk+p2M0stS6uxIWJpktA6ox86F0ke7gu90fdRbOG2CZGcdTlNLuo5sPtuU+D5rGcvzzbyOidd84FBSPD9x634g1y6QrUceOeM4Xt66nvWWoUHUuNZOWI1obGCU9sV1TNLyhzJCmJFh1CsKtMOwSMsxWKQFIg7qOjnfrnfJB3ht9coi/tSx863WwNTY5Apl2i0an9C2qVDE9m7ZegqUqw2bpiPNcE4X8zjOcduO84H9h6HutDNOhXLAadDFfItJa3Jo/dr4Gqs9PfIIrvsJ6P7Ys+dgd3tgEG2gHnr4KJRvve0BKM+K9UcO3R9xSqk0pEZB6T3Ynknqq6x7BGQZ1Y5Q2/DEPc1PSE4nIdcPsvUOayqxuA8d0utY82HtKRD6MI9VQud1RMIStiDjR75c+8ZzjxM/OA7ZZ8EzFDWg6pxqQAqFQqFYpdAXkEKhUCj6An0BKRQKhaIvWLXpGOI47voOSS60Q6lnSYIAvjNLaT0Ox+iTr5ED6wqYy2VbdctVM7/sk8eTTLfMfCwfNyTLf+k7xXy+cdjTyW5HHbZDR52n3RbpC0jDyiL24yL/J6GVdTrIcddqyCEvLBzobgekd+ULtEYlF4o61BiGhzFFRLGIa5PGRfG0U1Bb2rwZz7v1VKtRZG1KkZ5gmx5++Inu9vTGjbiv4TUS2OfVmp0Xayaw/cdmUBfJi9QBEaUQ77RwPDptO5bjkxugjpbCmNGJESjL9S9zpRLuO4L7lit2jdRp27ZCnUf6hSv83u793sNQNzSA++644jwo37Frb3f7yFHU4Hj9jvRvZL3FdTh1gN2X9ZSU0wU4XBbrjUjTTel+aDbseOVyqPVFdC85IhVCT/pr8pzj50qU2sHNSJcNQzyvbDNfe72O/oC5vMynDlUm4fT2VJ+KNVDyPBkb9S0D/QJSKBQKRV+gLyCFQqFQ9AWrloLzHL8bRilDDnP0qVmnrKCO+CzvoQmIavIoHUNbxNUGdJ6AslS2WoIaC8gOhcJDjfgc7rHb4E9a/nQVbXY5hSLblkjKYQVLH26HQ6GWHJfP2Q0TkW2RrV86LcwemQmbDw6pXSpjWHMYWBoqW8BzFsI5KA+QK9HaC6e624PDa6HuksuQ8qmWbYqFo8ePQV2rgikJUtHnc3MYzj0xjZRcfRHn4qGDNjS5WKRxN0hVNg8d6G5fdNGFUOcQfZor2DD51FBGWrJrcj2cm82apdWmprZAXaeD49GoWTpsmLLi1lvYTwNjlvYMfKKVYzzu1DC28cpLN3e3HxlF+vTBhw5A2c1EyhS6lyIKK5d0o0v3ehJhG/MhUrryfsmIBnRoiYMvaLVWhPSWR5S6pN1IATAupQbJu2QlJu7M1KfMpESV+Tlb324z5YZ9ISnf3hQ1zxTCba9dPrs4k+py0C8ghUKhUPQF+gJSKBQKRV9wUi+g66+/3lx66aVmaGjITE5Omle+8pVm7969sE+r1TLXXnutGR8fN4ODg+aqq64ys7Ozz2mjFQqFQvGjj5PSgG699VZz7bXXmksvvdTEcWze9773mZe+9KVmz549ZuCpMNK3v/3t5qtf/ar53Oc+Z0ZGRsxb3vIW86pXvcrcfvvtJ9WwJElslHEqNQfkIDlE2HWX5x45pLPTRB4+XxQaBPGzFDFpAsHtcpgjiyiyTWwDH1E4ZUCpwGUoKYdlhuHyKYiZE2ZL9iiy9RySytpYQn2MobBQ1ROiKv/GYb0oT3pFIvqmEOJxBvN47eecMQXl7dsnutsv/unLoM4ju6ZAcO1OA/upvYQ6zuSgDU3OUSh4aRFDhos5bPMF557e3Y5JB6nXS1A+a/tZ3e0mhckOj45BuVqviTrUu0ZHR6Gco1D3ttAuR0cwlcbcPPZxISdCwyPSPRwcuzixbRoZQr0oSPHmoQzRZt1mew0TYxgKHtBc/N6DNi1EsnxmcmMM3pcOT0sCL1uQzwqPb3663eGe5iUN9FNPhipHlBKC0tAzkhVc03I5slwSNybrzr0p3ZdPXd6bjgHnCC9tOVmc1Avo61//OpT/9m//1kxOTppdu3aZF73oRaZcLpuPf/zj5tOf/rR58YtfbIwx5qabbjJnnXWW+e53v2uuuOKKnmO2221Y61KpVHr2USgUCsWPH34gDahcLhtjjBkbe/IvtF27dpkoiszOnTu7+2zfvt1s3rzZ3HHHHU97jOuvv96MjIx0/23atOkHaZJCoVAofkTwfb+A0jQ11113nbnyyivNueeea4wxZmZmxoRh2EMDTE1NmZmZmac5ijHvfe97Tblc7v47fPjw0+6nUCgUih8vfN/rgK699lqze/duc9ttt/1ADcjlcj1phY150rLm39McyCUtjSZapzBH6UuOlTjTnjTVpEGkIuUtrzHgNMnS6iIlvYUh12ZQVnBTKOC6B0594AuvoYTTgjOXKwhnXk9UrZbxuDL1BGlYkhI1xphiEduYyH4izpvtRNrt5VN/c0rlVGg1aYRU7CnrUa+45EK0/P/FX/rp7naziRpKfRHX79RmbYrooIHXmmviOqa8WGtVn8e6DRsozXa1BOXpqVF7XLJoMR6mTYiFLpXSup9h0mqClp0jo2tGoS6f5zmNc2REWOPTMjIzQDrh+Lg99vw8rsMaHESdJ2rZek7/PkApOjadiv3WFnqFY1Bj+KVfeD6Ua2J8ntg3D3XtNs0vqT3RopvAp7+9OYVKHIl9SQeJ8X6X6wsz0kTiDq3PEWtwWD+RuqwxxgR0L0m926f1RRFpN3IdE6/l6Vm36NnfssbDz5GeeSz0I7leLUsT0zTPjO/rC+gtb3mL+cpXvmK+9a1vmY3CH2t6etp0Oh1TIo+p2dlZMz09bRQKhUKh+Hec1AsoyzLzlre8xXz+85833/zmN83WrWhQePHFF5sgCMwtt9zS/b+9e/eaQ4cOmR07djw3LVYoFArFjwVOioK79tprzac//WnzxS9+0QwNDXV1nZGREVMoFMzIyIj5zd/8TfOOd7zDjI2NmeHhYfM7v/M7ZseOHU8bAbcSHNftUkOxsMjhiEhGBrwChX9mvC+5SYufMg3FiUul/QY3icONW23piEtZGz2mAvBo8rOcrTv4xNLmgz+7E+L+5L69rrzsyI2Ovr7IhsmUoeOs8DcNhdA3mkizSfZox46LoK4YYsjzT1GotXQ2D6hfFok+qs5ZJ+rmwgmoG8zjjzdssPSXO4CZHQfGMTy61kBaKifCmBNyZs8PIa3WFPONM+w26kQTFm04eEA0jucR9bqE/SbMi40fILWaI1qt2bJU5ok57MOF+RKUH3t0X3d7/QRSbPvmHoPyzAKuC1y30dKpuRzOp43To1DeMG3bfOgQ20th+zsidLzVQOugnrBlsqqSVjIZhZGzdRVkLWZ3e6LREnE/O+yMT3QXZ6xNpRXPM8Sgu+KBldE92SaqzxEx6h5b71D4fUbx7JKyk0tTnq0b9km9gD72sY8ZY4z56Z/+afj/m266ybz+9a83xhjzp3/6p8Z1XXPVVVeZdrttXvayl5k///M/P5nTKBQKheInACf1AuIvhqdDPp83N954o7nxxhu/70YpFAqF4scf6gWnUCgUir5g1aZjiKPIOO6TPKK0r+CQ7VYbuVAZqug4HIa9MpcrwSHaPZlMRego87wZefH4wmLDI4v1hLhS38N6V7Qjo0yZvVqT1Qpi0nzyeQyflHwz22/06jjL/53CehGHksrssByYOTCEffq880/rbj9+4CGoe8e1vwrlyQm04vFFnycB9QtZ5HjC1mfzmRidOTSMtvzSlsjJYZhyOIT7jq7B0HDPtfuHIVrMNCOci+MTgj8nO6lOjGMps8OWSqhhtcqo+dQqWL/l1DO72/MlXNLQbmGovivsaEaKeN8tHKOwbKFFzR3DNX/rplET8ot4PZWq1QLXr8PxmF88AuUzTrfj7riUZXYO5/FjT4issxR27dH9HTdR55Shyi6JrT5nVxW6s+PgtYX03JAZFzK6RwMKrQ7z9KwTWjjrRZxqJktFmgRO9koh51km+q3HRmzlbxT5PMYUFs/MlhmjX0AKhUKh6BP0BaRQKBSKvkBfQAqFQqHoC1atBuQHQZfXzAS3GJMO0mO3I+xpetJfE2/qUFpbsG8n7tPvsc2w50lIQzHE4cv02Ky3cIx+lJGlhuB9c7QYiVNPBGJ9jkvrQcASxyDfzOuAelMqZFRvj82WJj0akC/XLuB6lg0bke9/4tF7u9tDRRzniy84E8oBXXtl9lB3u1NCP8Ggg3rFhFjOM0ipsh1aH+LkrM7jh7gOKMyPQrk4wBqQ/W2cUqrjQTyPF9h9XZ91TkonIdZTUfZrs7SIms842eAszVpdZGR0HOrmFtCyaO641V/aJbQ3ahzHPq0tlrrbQ8MTUDdcRL1lsYY6lQnsfNq+eTtUbV6P5sSnbzu7u/3V//UA1B2bfwTKri+0GXoW1CgVS47kYJnOJCULqZhElTAndE6qa7dJExJ6cWaWX5tnTO+9BCmvsbkr2o6x5uM6vBZRnhfblFLKCLYPerZaz3LQLyCFQqFQ9AX6AlIoFApFX7BqKbhms9kNB5ZZEROyzGBKKxShyfxJy+hE7Gor3sdkMZOFFIopPuk55NkjWkp+lrsOUT4u01+UnVSEV/L19PSFKHOYqUs+PvJYIbnjsiMu2wMlIpa0HmGmT99nfyDbx4MDFGbqk11HbENh33jNf4aq0SFsY20RQ32bS5aCSytHoa7oYxuLwm4noyy5bDDuS8rEwbDrfB6teFptDvWVdkdkadJBCihN7bxIW9j/PoW6N8pL3e0gxTk8SP0fk0P34MBod3v28b1QV2+iXU1BtLF07BDU5Wj5wxYRkr5QQSqvlGEbT3/eWVCOjRgDon8Dup6CCC9eM4z9cuwghu67qQ2D912cP0y/Zyn2ubwv2y3ORIz3lrxfHLr3HSbLRJGfXUGOjkvUqyPoL2IFe2zG5BKNLGM7Hdw3Fs/BhCUOtu/vsTez9UARPksrHv0CUigUCkVfoC8ghUKhUPQF+gJSKBQKRV+wajWgXBhaW3qhi2SURbNYxLDADlhqsAcF/patxyVctsSh8EMj9CKXM5USHyuthGLSbQrE+7aIbwbppif9ApZ9cX1s05NlpD2JH3ciPCdrWDK82xi0hsnIJiaj63Ndyy9v2b4R6qonKDx6jU1RcOWO50FdXdi1GGNMbQmzYRqZkTNFixlD/H4rstfnhwO0L4XQiz4tFNH6JYmxn8IcZbcVhD/z8AFbOxmrvySkwbWqaBOTduy+WacEdQUXdYVSDe11FuZsCHRGIbZpBftYyp6TZG9Ub6Ct0twRG/ruU5bfIId9Wp1F/a4mM336GDbeyPC+azXtsS593hlQ94ZffSnuG9kw83/4AmZuPrGEOpVP4fdNkQIjV0Dtjy29CnmrNXU6OFbGIS1ZaiMup3WgUH3SZlMhUPbYivGyEXEPcyh1lrL1lvgdaceGxp1Dw6UVD2rHasWjUCgUilUMfQEpFAqFoi/QF5BCoVAo+oJVqwG5rtvlNX2xDqjdQf4yijhdtC+28f3apLUL7FMu1wH5xM/miNeGGH5O7b3C+qNnstso0HlSISix9Q6vA5Jo87US5LVyyL5HOlsUsW28SMlN62hc4n4HRZrnpROYinn+KGpAL33xed3tfIG0vRJqDoFL3Hog0gonZJdPa0vC0OoMDml7+QFMueAIy6LeFRF43CTGuSiPza72vN6i3RZrcEgv8ngNUWrPw/ZGrQZqPnni8AtCY2lXcH1UpYx2O5nQEXMkQOaGSDuL7PgEeayrURvX5LBNw0PW4qg4inrL0BimsVg4YXWqgKypdr70cij/728+2t0u5Pme5LHjOWK1DbbwYvuZZtPew5wuhhfdQLr1DqfG5jU21EbRZr72XIjaGei6pAf7hu9vuy9b7XToectpXeTzNpLP02e3DEi/gBQKhULRH+gLSKFQKBR9gb6AFAqFQtEXrFoNqNPpdPnS1JN6BfHjbA8uPNxaLY7Jx8tljhXSVFOsPPtkBcIPyqX1RJ0I9QnJ7XJqb/aD8jxeN2C3OX03p8v1hV4Rk48Up+yV2lOeOHvfo3TFMVvM298SvWw4m/fpp5/S3d5/4EE8TgPbuGWLTWfgJKiRFALkx0s1WgfUtNqHk7GXHfnrCW+1lNZHJaS/JNKzjdYTeXTckNrYjuxvU9L6Ok08ViqOndC6LNbVGpVSd7tIfnouLUJLWUeIhV4R4Jw4ZQOmzp4/fry77RicpzH1RTEv1qCR91uLUh84tKYrKAidcB51wSjj+0F4PRpsQxzj+q+hITuPt51+KtTNL+H9XKtiWcL32VeR0jOIe7jZbK64L2aF4OcPXmtiWFuW44VzrdHA9ss04Zzqu5NQyhfRftaVeS0Sa9ayjeoFp1AoFIofGegLSKFQKBR9waql4IIg6FJwkoLgkGBiluATMSCKgZ3FOewRQpOJuuA3tcyKGATL29xweaVzGtNLyTnizBziyZ/LjvBo9ylMc6Vw74goH/Z6Z9pQMgHcL2GI/3N8xlq0lBeRejn7rNOh/NKX/pQ9LmWGbVWQmqnPY3oAU7cWMwUK8/Up3WWjLqhZtlgK8Ly5og0LbtSJOvIxZL5DNFUm6C6PuMqA9vVDkXYjwFDXmKx5QhHa7hHd2KpwuhIaWxEf2yZqrFVFCqs4ZK+vUce6NtE40vUqptDddhnpoaVjGI4vfzt0GlJl7RrS6HHHtj8/Ngp1zQaGlUuKq0y0n99jw4XzwFuB9ud7WFJcHll4sTWPvN/5uZHRsyAgGyL5SOLMqx7RbJm4p1mK4OUp0pKM0y+0OSUEtTEVzysph3DKh+WgX0AKhUKh6Av0BaRQKBSKvkBfQAqFQqHoC1atBuR6Xjd0WL4lOew6oXBQybHyvlxOKZTREeUchR8yP+uKeGMO52asVM8aUC6H/D+EYVOIreuSdbpoU5KwbTodVxyK+8UhS/+ecHVRZg1uw6ZJKM+d2N/djjp4nPMvQDv9sXFrg9NcQp3Ai9BiprGAabdHCyJ1Not91H4ZQm+4D8lDpCTSPoSUgrvhkKV/SHNGhCM71KZOk21YRJ8yf84p38UO5RK2obqI4em5kMbWk9ZOeJrMp5BtUcw4JJhIfik1teqoGxQpnYGh0Oq80FsG6LjhIOpsuby17TkxfwLqfFoDUKrY1OX1JmpAKWtwpJnK9BnSCswYTItgTO8SBzwuP2LtcVuky3Ibep227HlCup/5fpdLMjgMm9PUQPg36Vuet7JmLfUxeV9l6fI2YXC8Z7WXQqFQKBTPMfQFpFAoFIq+QF9ACoVCoegLVq0GlMSxSZ/KRy35xB4rHuIkpQU+r6lh6wuXrHmk1U3bYOx8WEC7GrkWgNfYhLSOA3UpSsVM11Muo9YxJKzqk4TTReO1d4S9u0N/W7CdDus+AAf7KYqR05f8s+fSvhGvxbDnzecxpfUVOy6EckVw9jm6VkM2K2mH0m771rbfpRQEPfy+3KbTcErx4WGZnoHWbRDvXivjtcu+AUsfY0yrRjrJgG0jZ/Pg+eUJTau0eILqsP2NCqZY8IQGFJOmyCk8HJGenGdLRvNJ2k+xJhJQuutaG++txglr+VOcHIc6J08pVRr2t1EHbW8SXpsk1w8meM7iEOp1rRpbIwlbrh67LNJBpF5E186aSVvcSz02YmQD5dCzwhdrjDq0Nsyhe1bqVrxeMGUrnkSu5aHnKaUJ73nWCd2nLea4akAKhUKhWNXQF5BCoVAo+oJVS8G5ng0TbQtnZHZfTimToSc+GTOzPMX25DncZcse2fgEFIqZCfor7AnhXD5zaUKf87kQw0yLA0j1xaLJHoWGJ0S3GBlGS1Y2aUzXLj73HaIiowypDY/sdZLEXm8uh+ep1ZESkgk6h4amsK6CIcPD7vrudqeJ4cX7H3kUygUaDyewn/9BiFlNI2YDIhFu72Of+iH2f7lijxtSxHa7RY7dOQw3dgVx5XpEyw7wnLGUYkpzpFNH+qguLHPY9bxYxPN4ObILqlmaMCZqdaBALujC9ipqEA0VEzVWs3Y7A3St9QWkS+MQr31iem13OyFqbzhE2rYhs4JSeH17BufTadusE3v4nUegrpBgv7g+2QOJy+XlD1GP0bOgNYk+9bgsbG9Wsuwyxpi0Jw7bnpizIzPFLsshPcs8WnqQpeL+T+kB6xH925Mx1d4D8rGnbtgKhUKhWNXQF5BCoVAo+gJ9ASkUCoWiL1i1GpDx3K4IFIiMhCnx1gFZXcjUAlGEvPXAIPLJUU/qAwumMGPSUKSNj+diGzwKA3aEFsDcaEI2K2znEsUyHBQ1Bw7bzAtdgeljj8I0PTH0PVQzZwkl0tsTXLVM62CMMSZFvr8iwsrXDBBnj/SyqYssoffd/k2omwgxnDhXRB47N2DD1V3qQ7bIN1KzI/3OC1DHSYXO1iSLmVyOuHTqSE+E5MYtChkmzj4VOluScdg49n/OtzrVWHGC2oBzhDOMtoVW49Bx5yqcssD2oxsj918p4zhHom8WI6xzKZS3Rek+hkXm2GHSOU8cRsulSOgZnJIgpHk7d3zGtndpEepyPlpGxTFORmnnFJL412GrJ/F3PC+rYNsbX2TN5fBoDtnmcHaZbTWkOc6WP9Kah620WMfxRft5X5f27UnPwGsGThL6BaRQKBSKvkBfQAqFQqHoC/QFpFAoFIq+YNVqQI7rd1NyG0esWTErW6NLLrTXOpwsKEhDCUV8POsGDpVdETuf0Xu8QymJw8Ael9fccPx+klIaBWFlnxLnnXE6CVHk45qU9oUmM/dM08LBfpKZhFtNtJ8ZKuBvC0LbCFq4tqdZwnUbUcOuHxl0kWteN0L9xukAjNVFhgYxbYJP61sqTbuuhtNfB7lhKG/cPN3dri5he48ewbTgw4O4hignUxTTmq2A+rTasuPO68o4RXrcscdaKs9THfZbQtrG4NBod7vdQF1tcgg10o7QUGdmcX1XtUTWSELQGxpEHa1M58lI59l3YJ89Zx7Ho9rBfhpca8c2oJQEjSpeu5vacZeWVk+2H+ft6Ahee2nJapdsPzM4gPvWRWrz1LBWzKlY5PNrZbsa1pMGRGqKDgmo5MplApGGIyEtPKKFcfm8Ha8OaTxsb8RWPfJ5KzUtTt+xHPQLSKFQKBR9gb6AFAqFQtEXrFoKLo5i4zzlJuyI0MCIXVbpE1G60bL1Ttbz+Ugev+I71veRtnFdylYo6L2YPnHz5P4bi3ZkPQ4VlBGVQj4d8YOYrpVDIFuCxuFQy5hCPn3fnrdNlCHbBWUOhRc7ln4ZLCKdUllEmm04b6fYK174PKibzhMVEFvaY/MkZdHsINVUa+LU3Thpw2odF6mZQpHC7x0bitxoYxtyORygWIQIuzQ2m07ZCuV2C2mphQXbFy7NxfrSEpQLRUuvpJz1t4m0SKNk+4nn+PDYKJRrDaRCYpEdMyW35cVSCcqROG/WQcqnWUHX9oGCtT9i2smhEOE4ZVd62ybXYB8PUDbVJx4/3N1utBtQt20buqs/sd9Se0EO6dHUQ1qwXscQdHkJ7HDNociS6o+JanWJJpdhzkzzM00r71FjyAGbop/Zmkfu6zlMsbO1lr3fe0LbKaMuQ54Hj6sUnEKhUChWMfQFpFAoFIq+QF9ACoVCoegLVq8G1O50w7B9Yb/hEPnpB8ijtgUnGZBdRRDg5TKXm8mwSOJUI7I4McJehEMgezIQCjqUbXsy4pc7rGkJit+hE/VkNRWh1glZB61ko85uGvzbfJ7yEIhssTNH0cY+baMOcs5p27vbCwtH8LhPoK6wxrV8/4Y12IZWizI+Bsjp33brnaIO58Tp52yH8tZtp3e3vQAvPk86T61qdQbfJ569jXOCLVsGBq0u0iB9pdlA/SITNiuLLaxzU9ZUxFiGOJ8aMaZumNi4DsqJ0LyWSLMKaJzrVauLtDqomYxPjUDZ8+zYVcnSJ6Uw8nabbhhhabT3icNQVcauMPkxO+5hHm2g5hdQV1tcsu3IFzEMO46xjay/yPslprDlXIDnTYTeEZL0wdoMhiqzpkvaGGd7dpa38WHI+pTsdXI5egaJer7XowifkZwdVrbJkfM0VQ1IoVAoFKsY+gJSKBQKRV+gLyCFQqFQ9AWrVgPK5cKuHbm0oMmYF6W1PZLTjzgNtYflnt8K3telXLotWosR5q2+5JGOE3CqXUGHdsgiZ6CAa1YiWm8h9Qzm0tn5XfKxrEdkZEMEqRxYW3JRO2PtyRf9NLdUgro86UllsWbly498D+re9ls/DWXZZF4rUqFUCM0Krjc6cfhYdzs3vAbqGvfugfLBQ9ZWZv3mDVC3bmotlHNCY6kuoSBRHEAtoN3ElAtG8OUxpdUepFTsmViTE9PapDRFrano2zmzectpUDe8dhzKR44dh3KjYnUf1kRTGuehSbt+qjBIOmCCA11bkPZGeNz6PPZL5OPanpro12CS0qnTGruc6JowR7pmG3Wq6UmbquLoE2gllCe7o5DShHda9kScFoHXyZkV1r+w9ZaUYlmbCYLldVpj8H7nNYx8j4Yy9Tc9N6LO8tpT4vGaIRxnTkESCR3UFb9lm7DloF9ACoVCoegL9AWkUCgUir5AX0AKhUKh6AtWrQZkkqwbnx6J12SHtIFh4iwDobEE5GGWUQpoQ15Y0lfOJ5+pUeKBDfgyEcdqkLtNXMv352jtgsv+Ty55d4m0Dy1aY+M6yMeGOavdxBGn7yZtSVx7mpKGRVx0EqF+ETftGoqoRekYhjEVwvF5y8v7A8j9j02M4m8Lts+TNh43aWEfF4eQs7/0UrvW5/ARXA8yO4faQHnRkunVRdSW9vkPQfn0rXYdTWjwnCcodUZIaR8iofu0KjifNkxvhHIstCZfpEwwxhiX5tegSIMe5nA+zRxEzefI/iegPFy0+tHIBK6NSRy8vkJs921SCu52nVKOCM+/pRn0iYsT7GOf0jEEYp1NaRa1vZhSpLcadl5MkN611MI5v2+/TeedD3Fetuj+YL046oi1PaQXdSjlhSfTQng4B5oxzmN5rIxSishzPlmPz6dQ3Jcp++nR+kIpPUUxXqvr8XlsmdcEkgTUm3Ye/DPlM0U1IIVCoVCsYugLSKFQKBR9waql4BI/66ZjSAVNNTyITc7XS1A+c6OlFS5+3ulQ52YYDsqWFKNj1l6EqTLHxU/rqqBU9j1xFOr2HUa65ahw/WhmFGppkN4yFCpeDOzfCEmC7XXpc98xT/85bExvhkJPpJfIyGWIs2jmKdx1bt5SXC7ll8gVkF6ZX7IUxCTRZsePHoTyOkELbhifgLqZBmYfHRhB+sgdtDTIOevOhLrxI0gf7bl/f3f72F6kfCbGMHXDrkM2dPz8s3E+xS7RNg3s88HQ0keNNu47P4s0oVsQfwvmkL4YHcew8lJpxm5TWP/s7AyUx8fwt3lB3zWIAkodnPOdlm1zeQn/VqUkp8aXaSvoz9qxcQytjhOizTu2HS5lqD3UQrqr6FgrniTGueaHeJ4NG+z9cYBCwXsypC7iPSvDnNn2xgvoAkV2W49SKHgR3jtRx97vQ0RJcxg/h4p3BJXmUHoYTu3QbNo5H9Jzjhx/ILybs7BGZDflUfg3ZEQVczHjtDnLQL+AFAqFQtEX6AtIoVAoFH3BD/QC+shHPmIcxzHXXXdd9/9arZa59tprzfj4uBkcHDRXXXWVmZ2dXf4gCoVCofiJxPetAd19993mL//yL835558P///2t7/dfPWrXzWf+9znzMjIiHnLW95iXvWqV5nbb7/9pI6fejYld1FwxmENUzP/zjUvhvL/8Rsvs/uSJQinQnCJDHWEl3rqcO5s/G21bLlpL0Ut5uCjyMN/4677u9u7HkXN4cEn8DyNBHnsjoindD3kvDOy8pApIzjbOCMT1xfQzi5ZdyQUxpn25hW37e2gplUctG3Okb3RMKVbTlLLgc8vlqBubAzTCqwZnoRyFNk2ORTOOplHXWHgbGtfs28f6lANStERR/ZYRw/iH1KnnLIeymkdtbOlhbnudhZjn1bKJSgbEdJdGEQ+v1ym1AFi33Ybr7VWwTYszON5ai1brkWkCwYUQizSKqSkBbBl1OSorR/0cZ5GMYUtO5TCXvjTVGmpge9h2o2aSOWw/wgJUSHqOocP2v6fWcJ9M05ZT+NujAytJj2V7i2Zsj6ldBi+wTnuCRuiVhVDtD1eFpKSniRTl3vPEBourq9Hx6HzcEi3BFufpQk9c8DiS1jxLP+IAHxfX0C1Ws1cffXV5q//+q/NmjVW5CyXy+bjH/+4+ZM/+RPz4he/2Fx88cXmpptuMt/5znfMd7/73ac9VrvdNpVKBf4pFAqF4scf39cL6NprrzUvf/nLzc6dO+H/d+3aZaIogv/fvn272bx5s7njjjue9ljXX3+9GRkZ6f7btGnT99MkhUKhUPyI4aRfQJ/5zGfMvffea66//vqeupmZGROGoRkdHYX/n5qaMjMzMz37G2PMe9/7XlMul7v/Dh8+/LT7KRQKheLHCyelAR0+fNi87W1vM9/4xjdMnnj17xe5XM7kcrme/y84BeM+lfY6jC1/+9LnY3rlq16OGlStZtd4DI1shbrIxTTCDtnetJv2PHGE6wKcBEnNobzlm0PivDdsn4LyGy97TXf7lXPI1d53xz4o3/R5/FJ8sCTT8OLfC1mCPLy0VedUDQGlqU4Fd+vQehCPtJqMLGfkUoc2ccLHj+GaqNEpq9UkNTzOxvWY+mByxGpADq3xODJ7DMr79z2ObRZrQLhNTdK0wiE7DwZPPxfb4ONv9+21qRzKDdQujh3GP6omxlC/c4S1U71G2kCK94/UcjqUArpUR61ADm2b+unxI7iW5MgSrjfKCnZ9VbWJ2oDj4m+LgUjVXMD5E+TxvAPC6smhNSDlJbTmmRqjVBSJvdc8gzpUp4OPqFjoewVa91PuWctj+7jdQv1udBLnXo2snwoiTYpP2liUkA1RaPuiQ+uWfMrR7RqrzTgG28+pD9qknTme0JrS5dtgjDGu0IvqZJvUY+MD9z/d+2RBxrqz40p7IDszs2fnxHNyX0C7du0yJ06cMBdddJHxfd/4vm9uvfVW89GPftT4vm+mpqZMp9MxpVIJfjc7O2ump6dP5lQKhUKh+DHHSX0BveQlLzEPPvgg/N8b3vAGs337dvPud7/bbNq0yQRBYG655RZz1VVXGWOM2bt3rzl06JDZsWPHc9dqhUKhUPzI46ReQENDQ+bcc5GyGBgYMOPj493//83f/E3zjne8w4yNjZnh4WHzO7/zO2bHjh3miiuuOKmGhTVr6XHKlKUv/svrL4f9OhGGV66dPru7HRv81A9CzgxILs9tW+6Q10inglRGM5NhzEhP5NdvhnI4aKnALYMYVrpxkGxWahgFuPczNny9SbRNPk9ZKgU50xMuSVkQZSQmh06HZOPTITpS7u+TJUiHQmxbDRtWu3YCQ1Lri5ilcklQfSPDmKn02MwclB9/ZD+US7G93hMUUTu8+Rwo3717d3e7UUba6cLTkLY9Y5OlEM/aijY9QYL9cugw0qnFAeFw7XLoK9JfpZLtp9YiUpUdB/eNBaXY7CBF0k5xzo+OYJ/Pte0yhhxZyqQUWm0ElVYcxBDnqIMc71xd0G4+tqEwhCHzpTqO5YjIsukYsnoht+/5hp17dRcH+oGHHoHyKZvtfbh16yl43EEcS8fFrLnSYsqNKRMuu+wL+m4kJPfuGOlHaafFDt1xjLxVkZaRtBJ7LJn52ZjepRKJoNJcziLd41Rty0yxeRyuTvSjI7NIi/M824yoz7kX3J/+6Z8a13XNVVddZdrttnnZy15m/vzP//y5Po1CoVAofsTxA7+A/vVf/xXK+Xze3HjjjebGG2/8QQ+tUCgUih9jqBecQqFQKPqCVZuOYf1ww/hPhfh9+AO/0f3/jRuRex7Io0VLu225x3yI2gaHLXs51FDWDNjQTM/BqL20g2GaZaFflBcxHHfp0e9BuXDEhiavXYOW/nseLkH5jjsxg2WY2vDKhDhhzjSZZSKjq4vcuUvpJKRduushp+0GyANXKZR3cMjy3M0S9gs7GHUaVmMZL2AYfJ7Ou2WLXYTsuMilk1RmXvyzF0I5ElpItYW89UIHtbPGktVbZgdwTnzvUbTmOTRvefc9h/HvtW3DqH+dt3kUyuGgnYtTazHs9/AjeJ5W2fZFm3SQrIjHdUUcfOjgHAh97NN2jNZPp4l0Jnkf+yVHIdBrRcqLahV1kGobtYAFkTIlIVuYhMKy8xQy3GnaY2XUpogtjJp2vB7d+wDUzZ1AbUnaBeVHcO4FDZyoLmWDHfDFvRTj/F+D0dPm9DOsbkirNUypQu2v2PuhUcPnBpsBZQllPBa6Sq1Omg89Gxxh4RXSve9QFmlHZDVN6BnJ+jDrSWkk5kEmrXiWt/eB4z2rvRQKhUKheI6hLyCFQqFQ9AX6AlIoFApFX7BqNaDXXX2BKeSf5GXPPNXy54M55J5LS5ieYW7WaijNCq7lGZlCi5zBtagfjYxae/2wiBoE5zcYn7b1PqUVqBzCNSpz9+/tbt/7yLeg7rbHkbd+eBaHJHHt+gUO3+9EyBrnhT0Kr/vh9RWOOJZDFiBxShYgZE8jU3/H8cqpd2UKjA1TmGZ7ZBB1KplOgq2DTjsDx6rTwPUVgxN27HIFXF8xN4cW/6dutfrRg08ch7p9x3C9y2LN9mOF9K4Gec6neZwHbt72+aatp2FdhNd3aM5qisdbyMOPrcU1LHNLi93txC1B3VAR2zRKa3DWrLFjsGYYxYzNa0eh7LTsmrRdd6NFlOuhBjEqrGti0ovyRdQgSPqDNCNxRDpnymV7fSfmcc1ctUzr1VrWvmk6wfnfOIHzJ4wpRYRYk/bu614Hda+7+mehXBwQ9w/pWxm3X9yz9TrOyxKlIKnjEjXzpS99u7v9/37881DXdFBj7AgxipyETLtJqRtCkfKFpBvPoW8UqnfE/e16UgN6duuA9AtIoVAoFH2BvoAUCoVC0ResWgruZ15ythkaePKz3jX2c/jEE+iKPPcEpm/Y9+hj3e0165G2mSArmMYsfrJXjlo6ZrCAdNHYGrLN8ARNQnREcQRpnLhg7XfWno7u3R/8ry+F8tI80oaf+Od/627//V2PQZ0hC6A0EZYa9AXsekyj2R1iyqo5OYGhsEmEB2tVbf3Euo1Qd/z4XigX8+OiDWQp00D6NBbOzksnMHy4RaHVXht5hWO77Tyo13BOlGewT5uZ7bc4w1tgvYfH3SLmjD+Nf6+deSbmrmoQ9XTgkG3H5o1I/y61Mbx1rm4poeMGOaq7HkL/xViElQ+N4hxw55G3GR/EsTx0/73d7X0Hj0Bd6GBfvPB8a2H0koueB3XbhnBO7LrDZv1NiMeJydV5nGx9TizZNtd9PO6JEoZALwjWql7GcWXH+kbLlitEd4VNnHtnjGM//l/v+z+62y+8DJdOVI7dC+V6wc5bJ499WBzErLlBzs6nkUFaakCfA3GKFOMrX2ptxr77nTuh7u795CIuXKqjFPspl8drjVz7LGOLpSDEfduUXTXt2LK07cnSlan5f4d+ASkUCoWiL9AXkEKhUCj6An0BKRQKhaIvWLUakJNWjfOUZX25YvnyJx5H23RD+sTPXnN1d9sbH4W6dgP58cWjmL1z/vCj3e0Dcxh2miOL+eKwPfbgCOpFo2sw9HXT1jO6284Q7putwTZNhxiC+8s7rc3H944hJ7z7AGZ5dES6iYSymjpsjy7CTsMQ9ZVjs2gTE5I1TyrCjx0fuec0xWMlIhwzIBuPuInXXhOZMzdtPRPqOmP42z0P4DzYI9IzZE1KJ0EaVyzCykttbENCYacbp214a9jA/j+xG8PtZ0uoW738V365uz0+MQp1zRjP6/l2ju+87EVQd/O3/w33DSynPzKAOsLQGI5HPkOtaXrAtmPcwzY0KFT5yJy1ivniragjnLoBNa2X/ozN97X3PrSi2jiGNjhzR1F78gZsOHhtHnW0kWFMm3D8iYdtweUUI6hfZMKqyquXoO6XfvoyKP/uu14N5ahk9dZ9t38F6loLeN7RUasP1yPSLtt4P0c528bNZ+Mcj0inHSjgPC4fLXW3n38epny541G08JKpaFyH5r/BfurEto05D59zMWk5HF0tM+NiGLZqQAqFQqFYxdAXkEKhUCj6An0BKRQKhaIvWLUaUCGKTCF68v14YN5y0edceSnslw/JG12kiK4u4hoComNNbnAUylvPtJxsuhnXDeyjdL8LYo1HMoz7djrIl4cDliOO6li3xsM2LMyiNc/8ccuJZ2R7kyO7mmpkY/IT0lt80jY8YZ/PdjqcGtgnL48gb9eWeLQWyaHU045r+eaxMVz/MTyCfHM+Z/nkDg2WV0CrkTOf/zNQlmmfH7oH12mMFzENeq1h+3RDEecPp2L3U2uRMzKMa8FCyj1xxgWY+nv9WTalR5JgG0bHUSecnrZ9enDvfVB39jrUQULHtnHtulGoG6E1aGkL7YN8oQVesB41n3oN+/xE1V7f3uOLUFfu4NjdcrvVqbZNYD/5ZFk0SKkRjiza8RggC6yywXVM7YZYa5LhvCwO4287LXtfbl6P/fLf3vRrUK7tuR/K9z34HXselHzMzBGcI8XQ3rNrRtCKp0DpuwfGbP9Xi7he7UQdn1fD4zhnCsb26ymT2IcDBdJ1ROrvgFKbpB3UhER2DxO3SPNxKZVGHscDzinScKgGpFAoFIpVDX0BKRQKhaIv0BeQQqFQKPqCVasB1dqpcZ6K6z/l1O3d/3dI22jXkONenLNre2pLuG4jP4lptken0adpaMr6mmWUosBbswHK+++6u7tdIk+tahvPO7nZ6iQbTkdrfU5XfPwoelTde5f1vluk9L7tFHnfsGh5+WaEfD5lCjZhIOzzyZ49H45DuVbDtQ0Dwnqf1wG5HmpCfmDPnEd63LTID83rWM7bqeK4To1ugfL4RkxvsG7c+v5ddPkOqOs4SOI3xPg4Dq6FmZnBtT1ubHW10Q7qCLvu3AXlLeefDeX8mJ1vlUXi6CMs+8LnvllCjWFyAvWvAbGOaWEGdYMDh3H+FAOcx3lj+3yiiGO1YRQ1h3XjVjtYQ0ZlM1VMZ7DlFDseg+T9dvwIah0NShXSMSIdQ4ZeY60Ix6dSsrqOm0Ntw6O52Gha3erQMUx/fdMnPgHlyQw9Jt/4vt/vbg9Moqdkq45z85N/bo/1b3fi+rQN06iHnSU0ug0O1nXmMDWIIb3FG7FjMLoGb6aJYRyf8qJ9rsjU5MbgvW8MrgPK51Hba0Sob0f0XJH+bzJdd8Z5G5aBfgEpFAqFoi/QF5BCoVAo+oJVS8Hlx8ZM/ikr+U7Tfva5daRt9j+I9v+zx+xn7IbTtkKd28ZP5/oi0hUF31IQcQ4/U3MTGDZ7+uXWymN2AKmLA/c9DuVSzlIqw5NIrwwNYIjt+FqkBUttG+J5oorUnlPA80rbD5/CoUMK2ZaZGWPK3VAsIgUXUKbPRNjeJwn9dhCthqo1S20MUmbMdgs/7/OJ/XvIpVDwhWNIc85XkJpZM2VTI4xsQnouTJEOyIlQ604Jw963TOK1xrFt4/133gp1Z//0FVAe2Xwxnqd4anc730DbJ38Axycv5ttQHv8urFGKBSOskZoO2eP7OG9bbTyPJ3jQUoZz4jilAnFSe163g+e5/AxMUTAsQq8PPLob6racinN65jiOe7tmx3qujZT0DI1PLKyFiK0zCzNIFXuyGynNwGNPYGqTd930TigHo3autgK0Bwqnkf56/X/7ze72gQeRyvvdD/wulLecfUl3+9gMzglDWVmHhyhjcGbvf4/ShmzbtAbKB+YsRZrGlLmXfuv7do5QMmRTIErOkK1Po2HHMpDLNRyl4BQKhUKxiqEvIIVCoVD0BfoCUigUCkVfsGo1oDBOTfiURUxTWMXsP4ahipNbke/f8dKf727Xmqj5HD2yD8qLhzDktnbQ8rfD6zD0MlxLNixDViuYOGMb1JWXMER1z+6HuttFss8fKCCXvv8IhtU+MG954YZL6Zdj5FmLoT123EY+2aew8o7QWNhOp018v/FwmqTCxieJ8W+Y6Skcj9x6G0I8VkR9wk+RW2+LtBtRgmOXz6FtjKG0D/MVy/8vHUZ+36O0207d9k3lGHL299z9HSgPTdiw2Yufj+Hd67adAWWngDphmlp9LyDefWQCdZHTT7PpDU4sPQB1oUHblTGhORY81AXbBvu0fAL5/8gRcyRBvSWisTSifuM6TL9QIMucodCKB2efj6kCnngY77MozlHZ9k2dLKMem0HtzxE6bcrhxaSHTY3a+fZ7/+03oO6aV1wJ5VZIz4oDNg36ANk1DY/isyE3YjXTrZfjMotP/MPHofzQv9nUDnu+/b+g7vznoZVTUMD7pVayYeUJpTIZH8b55Qn/oIzmXkbjnglLKcfB50QakQ8RaTu+I6yRxHNarXgUCoVCsaqhLyCFQqFQ9AX6AlIoFApFX7BqNaBWOzXBU1Y8lbrll7eddR7sF1I6hqrQRWodspgZRi49SyhVbc3yqgcfeQjqikfwPGMT1prHpW70HV6fYzWWR+7AdUu3f/M+KD/uYzz/48JSI/TRCsY4bO9ieWyPLFhaMa6fclzL3XqkLfGfJS7ZHyXCbicim5sO9WlB2H64ZAgUUAri9pJtf4nSaBcDbP9Ai9asCGt+J8D1Xc0O/vbAI3ZtydEDJagb3YyWSy98uVjrk8f5s1TBa58cxPN0KjbFe9ZAbc+PkCMfXWPn19o1o1BXLVE6g3G7NmNqFO2lBsdw3YZDY1uvWI2oXEYdoUNrcEYG7fUWSEP0WyUoHz5idc+RAmo8wwHeD8daeF/Oim4sO6jtLZZQ1/GE/dRQHufI5lG8R//2xnd3t8/dhuvtThz+LrZ/H+pUQWDv6QNVHLuxUzZCed1ZF3S3wzHUvwprcE3dRT/9wu72QB41rHoN9W13APsiq9vrdTz87WZK7xE4VhNtk4brezg+jkgP79IzJaCxq9dRc3Q9Oy+kfqRWPAqFQqFY1dAXkEKhUCj6glVLwbXjzIRP0Wmjo6Pd/5chwMYYUyF7GmkQHRHtFPgYOrr+VAynzARllyN7ncd2o73I4hFL4xRc3Le8iFYjnshAOFehMFkfqYH5iBxwhZu0a5AGSTL8zE3BHZuzmpIVj7DniMkCJPDw0z+lsM2OsOIJQ/ycDyla2nVtG8kEuccRui1sllptpGnSHJZrpRNQNiID5PwJnBOVGp5ndsaO3dAY0jYveOnLoDwwYefM3IlZbFMdx/1EC/t8aa7U3fZTpJLcBOmvpSUbYrtmFGnYJ/ahtVNTZL79qTMvgrrxSZo/gzjnC4I67lAYf0Iht4vCQbo+i/1dovD1E0dt+9tFpAGbLbIWSnDO1EX49xLRcy3KjBsY22/nbUZK+m//7N1QzjqW0npk7yGoO3oUw7uzE2jjMzxk58UILZ1Iq3h/x0v2twPkJO9k9De+b+fItstfCFWdGI+7tIAu4iPG3lyFIj7byinSw3nx3GgaDMPuJPhbV9zfGfkbNar4vApCvJ5YOGn7gbj5HQ3DVigUCsUqhr6AFAqFQtEX6AtIoVAoFH3BqtWAHCczzlO2D2lieeEmaz4RvkMzYTHjh6h7BC5y02lMFjOu5S3H12F4q0Mh3Y/c/j1biIhTzZBzzQs9puxi3QkH+f79ZeS82zJcl0YrS+naMxkSSWIM/a2RJsvrRUmCWoDnYX3g22M7FJ4bxaR1CKv3JMXxqFVRB2ks2fN6BeKay9jHmcE2VkW/dWqog8zN42+nT7E6yPnPR+uUSg3t/1vH7fXMH8RQ3byHGlC1jVZPsUgjMjeDGTmTBOeT54m5N74J6jZvwvJc2d4DJyiFQiGP437aJrT88USWVp9S1Dpkg7Nu3O77SOMeqKsa1ExckfZhqYHXVqX7oRxjGyvinm00yB4owvk0VrDz9l3X/ALUzT74TSjPVexYvuhVvwZ157zg5VDOEry5ysetZtSsYdqEo0cehfLxw3bfWhXn2vqtaNMVDAiNiNKeGAdTmYwU0P5rep1N73Hi0MNQt5FsiDZO2HugNEtacYbPGCPSoBiXMvX6OFZS8zHGmCC0/eYIm55nF4StX0AKhUKh6BP0BaRQKBSKvkBfQAqFQqHoC1atBmSyyJinYuhrSzY+3qfUukkNOeNUULBLVbRYLxQonp/4zdywrR8YQL0iofQGnmP586UFTL8wPIox+UNiHcFjDWz/oQg1lHKKfLmMp48i5F8z4uzzOXueiLjaNq2ncITuEwTE89J6kIhsY3yRPpqaYFxa9yDX8zTpOBtGUEPJ2lYTqjVw7FwH9YpOB6dupWLPW62RBdMIXt+m02yKiEod1zkcnClBuThoLU5mj+E6jeE8lsMEjyWvJ6MU46UFvL7Ut32exjhPR4u4VmxmxlrDPPwArRE6geuamrNoSxQM2vqU1nsVB3FdzYljdu1P5RhqY0mTtD6xlich65d6B+dEKUKFoCLSKkRk9x8EpEuN2jlTegI1Nz+P+vC6c2y6jHAQ00l08qi9JnnUW4Ym7LjHx7FfnnfWdvxt245lyveooXT2jn2u5DxKr0K6rVtATcjEduyCcZw/axoHoPyyF9jUDns+cx/UOfzcE3Zm7RjnMEm8xqFvlljc03I6ZfiYWxb6BaRQKBSKvkBfQAqFQqHoC1YtBZc1Wl1H1XjBhprOHynBfq0FpAJmBVVQq2OI6tgoUj5rxvAz3Mlb+issIBVWI0uK2Rn7uZ908Ds1pIyiw+JzPu/i5++xR5E2SAzSLca1Q+S6OFwB2et0RKh4QvY5Rcpg2e5YeojtjTyiZhyfLYCEdQfZ65CvtklkuHeOXHnzREF4lj+V9kvGGNNYwjbNzSPtudi09TmMtjfrtyEt5QzYfhpcg3ZMCyLrpDHGfPp/frG7XTEYNrt5A1Ktm6bwPCax/UaR+ibO8FhrQrtv/SjOtU4b6RYjrGwSSl57/FAJym4Vd8iLvonJnZyceUwkqLJ2kyhoF0Pd2+JQLTpuh9yX0xz+tlGx19do47UbF8+7ZmC0u5018Tx7D6Gb9HlnnG+PS6HfRaKDW+WD2CbB5QchPjdyo+g8nYm/4/m+c2KSCMQSB8eQXU2L3MmpjZ7IkDq6FpcPdBbQKumszbYfJ0ZwDhxr4jyNBJ0au3ROotTDEG+utqCZU/GYUApOoVAoFKsa+gJSKBQKRV+gLyCFQqFQ9AWrVgOq7Js16VMawf6HD3T/f+4gZidMO8QnC960MEIhqUQvZ23UX1oNy2dGZJUyMrEWym0RDl6u077jGLaZBKPd7ZqD+zbIuqZD2Tsdocf4ZInTbrOdi/17IiPuttlCHSFJIrEvVJkBCldvUsd5IgVDRBy373HaB1ufUih1QlZCXs7qbinpCEs11HwqLeyncMBy05NTyFMPU5bQoQmr3SRkLz9+CobjvvYNv9jdfmQ/zpfde9CS5YEDqFc02/bYTcoUmxocu0BkpdxEYfzDPt6mnkjh0aB+aCeoXeYojHaNsObP0XxKSGtqt+3cbNA4R6xfiMuLXR5nbH+tiaHKvm/v4TjGPi7mUBMdGhDXHmF7B9bh2F3xs/+pu52fQq2PnJx6LIwSoXV0aFlCq0HpS/L2fndD7FPXJzFE2OBEdK+TVGYM9UVN2ETli3ifTU/g9U2O2hD1C5+HWvfR21BrygnLMk7x4lE5obQinm/nODx/Upp4y0C/gBQKhULRF+gLSKFQKBR9gb6AFAqFQtEXrFoNaOnYCdN5at1Ic8lqEI0GcpIx2X5kwo6mQgsbYiJ+J8mO3k3t/gFR3B1KBxB4lksvDJPdPK35OFa3B3vgIMbru0T8Bj7+TeC4lp9lWwzj4vU5Mg6fNBTXJb1FtB9TeaNuY4wxYcCcvq3P01okclIxrm9/225Q+gta8hSK9SGLS6j5GOqXoXH88eRGq5sMF3HfIEN+PxK2MeE46l2Oh2vHRoV8dD7lGy9kmLLjyAxe/EzZlgs0TysN1NVGh6zGyOuyTIjzS45Xhyx+wnAUyrNNtAuSKZXLDdQYfEqj3Ja6FbUhS/Fe8kUK+w6l3Yhi/G1C+kAEi5mwjweHUE+V4x7lUct49euvgnJdWCO1Kpg+ohiiPuzmcI5HqdVqXE5R76CG1WiXutsBWUglhoQdcS9x0upcgFplfhDP01mw65waM6ghLh3HdPHHjtsUEls24rol36CFUSTWLqWGLJZIt40pPUaYs2Mt9ess5at7eugXkEKhUCj6An0BKRQKhaIv0BeQQqFQKPqCVasBFQbzppB/snlTa60tebnJ60GY77dln2L92w7y7uUW+WQJnr7ZIVv1Mv62MGrXHDRJMzneQS3guwcs53q4Rny4j+uYiD43udheRKuD53HJVl2m4fZ9PFCaUhpekY6h04mpBjWhfIBt9sWij4R87wytA5IWYqUq8tadcdQgco7ti+FR1HiOzRyA8prJLVCOQtvmxTpqA2MDqPMEwm/Ma5WgbiiP+xqhscyeOAJVvoftP3UDtnl0zI5Xh2618gLO245IhRxSemi3iaLigNDdHBLdOvQ3ZUJpw4+V7f2zhtaotFo4R9LQjkdCOlpPqmaxrswlHapCaapbCemRYuzm5nGdX5FSXJx39oXd7Wve+DN43AjHY3jI+u0lLqU5SbFNSUxabM5qikGGbUh4PZ5r54xMS2GMMSQbmkSkSWk3S1DXatNxq4ewfv5wd3vhCUyzUSevykdFlo69hzGVhkcpuduO7RvK4mJcWifns1Ym9LtEqFpZj8L19NAvIIVCoVD0BfoCUigUCkVfsGopuCA/ZMKnrHjqjg0lbdOnc7WBtM7agr2kPIWzcgbIFnnZS/eaAoX5epSJ1Rd2NWkFv1tnYwwdPVqztELkIsXjOkS3cGi1oMryeaTrkmz58GnHofDcAKmYhggXzVP+AodCttlWIxGW8iFZ65NrCVgJ7T+GIc4XnIKhsF5qxzKicR4ewTaWaki3hJk9Vr2BNEE1wjaOiXDjoQqmXximjApBYKmY9ekWrPOQIsl8nAdrx22bjy8hRZKSfVNLZA3lsHeXQrhbIutmh8YqItubgMZWptJoRRii7XpE8YrUIXGEc61A414XbYopw26TlkO0Y7IsEmHAgYfXszGHffprr3pJd3upiaHV4AdkjCnv2dvdXjuGIfOFQeqXENvUESHe1QaeZ2QYbblCkeMiNtgvDllgeYnt87CGodMHHsXw6DDD59PhR/d3t3ffjfumROVXW1a22HsIqeOYnzHiOZLz8QbIDGVSpqUgMnVLENi5l6UJmU09PfQLSKFQKBR9gb6AFAqFQtEXnPQL6OjRo+Z1r3udGR8fN4VCwZx33nnmnnvu6dZnWWY+8IEPmHXr1plCoWB27txpHnvssee00QqFQqH40cdJaUBLS0vmyiuvND/zMz9jvva1r5m1a9eaxx57zKxZY+2+//iP/9h89KMfNZ/4xCfM1q1bzfvf/37zspe9zOzZs6dHw1gJdRESuu+Yta85XkFetE7W74OCh/z3MO5/B7m5mFyGPPDIkC0XRygemjj7XN5qAwcaqCO0Mkp/nVkeOCWrkYz48Yzsz10ZLk18ckD2KFL3KRZZ80ENQoZpy9QMxhgTR1jOU2hyKtIoRCnZHZH7vC/adHAGj1tuoE28SWy4aODhgUYHcN/6Is4DR4R4DzjIY+964CiU737A/kH00hftgLp8hLqO27Fju2Z0AurWDGEfT1DKd69ir32shfM052CfzmdW08p84uhJb+mIMPOA0qUXyE6nVMWQ9ExY73uGdEIi+H2RAp7tmhptLDcjYfFDukGlRVos3QOVmtX7kg7eZ2969y/jeTM7Pn6JUpscQ03r1n/5Tnf7jHPPg7rhSZxPzQ7+dt15NuX11JaNUFdbJDstt9Tddihs+fgc6i9uy96H5YNPQN09374PykP0vIzF5XoJatRNSsMxX7NjOVNCPTXN429zwi6LZCdjaC5yru1WyzZK6kHP1ornpF5Af/RHf2Q2bdpkbrrppu7/bd261Z40y8wNN9xgfu/3fs+84hWvMMYY88lPftJMTU2ZL3zhC+a1r31tzzHb7TbktalUKj37KBQKheLHDydFwX3pS18yl1xyiXn1q19tJicnzYUXXmj++q//ulu/f/9+MzMzY3bu3Nn9v5GREXP55ZebO+6442mPef3115uRkZHuv02bNn2fl6JQKBSKHyWc1Ato37595mMf+5jZtm2bufnmm81v//Zvm7e+9a3mE5/4hDHGmJmZGWOMMVNTU/C7qampbh3jve99rymXy91/hw8fftr9FAqFQvHjhZOi4NI0NZdccon58Ic/bIwx5sILLzS7d+82f/EXf2Guueaa76sBuVzO5HKci9aYg3seMYWn1hOkNcst5jLkOpuUo6Aj7MIrtA4odGgtj4tcdMe1v/XJx4dTG9dblluvkx3N7DxqQqnwt3ApJYRP6ZYjhyxaxOIkj+x1eK2PJ9aLcLpuRib6phO3qQ737RAvn8/bMeA0D66L19cWHPFMGdcBlRq4nkKmHPcjPGePxQmR1SKbt1kzClXmlNNOh3Ii7F3ueWAP1P36a38KyiMFuwbk8BEc18OUMuKJY7heJBPaRyGH+lCH7Ggckco5quK8HR8fhbJpWE6/UMT7oU7pAAqDeN6WsF2KyXJpiNKTRJlYgzaEuoEcV2OMaQnxb8nDCVSn1Ou1NuqRSxXb5hHSPbZOYnry6j67dmZxL/b3sX04PvWa1dluvmU31IVFvNYdl2+B8jkj9o/oNMBU36aAv20tCo2xjmt7Age1pUSkUD++/xjUtUvYT01aC+eJ9VVt0hQrtJ6wIZ4jHRfr0oTW/YnplqTYXod0wg49VwJa83WyOKkvoHXr1pmzzz4b/u+ss84yhw49KQxOTz+52Gt2Fgdhdna2W6dQKBQKhTEn+QK68sorzd69e+H/Hn30UXPKKU9GjGzdutVMT0+bW265pVtfqVTMnXfeaXbswGgjhUKhUPxk46QouLe//e3m+c9/vvnwhz9sXvOa15i77rrL/NVf/ZX5q7/6K2PMk5TQddddZ/7wD//QbNu2rRuGvX79evPKV77ypBp26vr1ZuCpjKgl336Kpg5SPG6Cn4AyjNNzKEy552qR6nCElUdArs5LS0gfLQq37JaH9MR8k+wrfPvJWyBrFBMjldQhmxJpoZMmWMch2x3RJo8sTdhCIxWOuL63PJVnDGZANcaYWISOu/wFTu7MrsweOYzX/tAhpFDOmLTXlyOKbS1liyzkKXxdWNCEOWz/2CDSCj9zjqX+dpM10mP3Pw7ll77y0u721u1IWR07ihTc8QMYnuuJUOVSqQR1QwMUYptf392uG5xPN/3Lt6B8dM46IU+NYr/sOBcZivEC3gNt4f49PYBz3CXKWobnlmlOt8iaKhXjs0Rh/B2ilZsRhoY3hZ3W2jzOxYF53PfoQwe62/fvRqalFmOfVhx7fRUXw65nD6Dr9gUvQt3aEfZNhRApuKyAc6ZTshRcdQmP26ojLXj8Mbvv3BHUxfM5pBvLDZy3ch1JHGA/xfS8OnjYnlc+f4wxxuEQaXHPOkzX0b5hiNSfdDeLxLjzs2k5nNQL6NJLLzWf//znzXvf+17zwQ9+0GzdutXccMMN5uqrr+7u8653vcvU63Xzpje9yZRKJfOCF7zAfP3rXz+pNUAKhUKh+PHHSZuR/sIv/IL5hV/4hWXrHccxH/zgB80HP/jBH6hhCoVCofjxhnrBKRQKhaIvWLXpGBp+3G1dLDIm5obxnZnDSEVTalrtoOAi9+kViJekLKGOEDSqVeRf2ea+41qevhojJ1xLkbeOhVV6g7j0Ac44SFYqTmZ1kTRB3p35WJkdkznYhFJPyPBJtlnxXP67BI/lS08jF6+nSFRrOGJtcdwCCkaHl5AfXzNi01jkyf7fJZ2qQPrdoLAlqjfwWod85NbP3m5tVkY66Lxx9ASO+5f+xgbUmJFRqEtI24hpPm3auK67fSIij5MIw6PDATvOX/76l6HuRB3PM7HxtO52nhyjZik9SZShbjgqtL/QI42U5lcqxp0zBHsh3lt1oXc1EhybJcrWOT6BmsqSsI0xTZwT1RPHoTy7aPWveBDvu7iG/VQIbf0ihb0fojDyf7t7F5SLbavVbCJdbdP550K5PmvtdhYPYXsrCyVs/36r+7iG+xsfZi6lonADoQHRfOrQc2N23oa2JwlOksDH38r7P6Z9PbrvMppPjUZT7CuteJ6dBqRfQAqFQqHoC/QFpFAoFIq+QF9ACoVCoegLVq0GFPgFEz5lU1MXvHXgoL5SpHUoLWEn4pKVeIH0Co90krpIWZB3iZ8lPakq4uUfnsHY/yalsE7blp/NPEplHOO+rst2O6K9xNlHEdv6iOP0aEnIefui31KDnLCbIWdfoLUkfmDbmMthnRdgn0qXpU6M/T8TYxsre+26mudNjkJdMcT2pz62Medb7SbvozZQKqOuMz1ldanBrfg32Pox1Cd+/oJXdrfv+9d7oO7b3/4ulLMMJ+Oex+z1xLzuZwD5/krVagdDCWpW6zZheolBwbVvnkA7I147klAKj/EROyADIfZTlfbt1G15mNJHlElTqebsuFfmcD7lPbxnzzgVUyM8+Jg1Kp4K8b5bOET2TTU7yase3pOuh9de9Oz94US01o1SRoQOjt0VL3lBd7tF2vGR792JbZq1qbIj0r9qS6QlR8JWzEMdMD+AbcpojWOU2ut16dshcXB+1TL5HME+deg+TFJ7Hp/WF3lkSdah9V+ZkeeRmvSzS8egX0AKhUKh6Av0BaRQKBSKvmDVUnBRMzOd5MlP30BYSeSR8TFehFRMsWjfqUmEn+8mwc/LqI2fooGgv6QLtTHGHK3iZ/hM3tYfqSA95OWQrvBluC59orNDRNRZPkTSD8l2iDKZSlpthLJz5vNYbndsvx3Yh6GjTob9NOwNQzkvKDmHwjQZ0pWbor1NuYaUT6Vpy9smMPtohexbhgfYQd22o0rjUSDH8ZpwsR5bgxYtZcp2eedtN3e3ixW81stPxdxVY6NIh80IV/RqjJRbI8OxawpX6xNNsjMawjkyOmJpwkoZ+yXn4xxxA7T1kdYp7SbOxYBDq+u2zTE9Kio0lsdEltZ2StRRRCHza8ahXBVLExYow+t35skGKm9D24+eQCun88ZxzmQySy79rZ1r43i84EUXQ9nP22uoVfE8tQZaMCUi5LhOmYejDi/1sO1w2PmeQqszos5k2HZGz6cqZWxuSzsk2tdQBgFHlGN6PmXk3s+QodcOyBZp785PA/0CUigUCkVfoC8ghUKhUPQF+gJSKBQKRV+wajWgQqFgirknNZlORXCuZHdSyOMlSKo9czn0EvlNl3IJZCLUukRhmzVKo7Bn1rYpHUSefcBH/rNQsL/1yO6cM4qmFMI9ULR6kuPhcQcGUGtqiTBa5m45vNII7WZgGDWGwSJeT450Kl/oDDGFgocU2huLFBINChFOE+ai7Xnue+wg1E2dvxGPS2k5PJEOwKU608FyedFqM+UIrXjGRlBHaAvNcbFE3H+Ac/Ho7BPYJqFL+R3KVErpJorC4v+ULaglzTdx36rQJAZccpl3MIyfrXjaYn6R2b8xLdIkfBv+XaNMxEukbVREE1uUNmR0FEPbF5awzyMRjl9xUNv71H37oZwXOtsU5RjZPki2MR1bblLo8dr1qP1dcukZUK517NKKmMYuorELi1ZfXUtaaymjTKW1ue52J6KMpx4+jygzi2nWhabtYp/WKGNwnK2UMoV1W5HKhJ6ZPJ9Sev5COlXQfTQMW6FQKBSrGPoCUigUCkVfoC8ghUKhUPQFq1YD6rTrJniqee22ZauzlIhRdv0WFiGBQfKzQNxnh9LNtkRcfskg571AHHg2YLtucgj55LSFlvJBYM/DKW4LlN7Xo9S6meCbY7KuaXfI9kNwxAMDqFk1aH2CXF+0dhI1B5dyl8dMRot+zBVoHRNx7alYI8H284vzuL5C6iCNKuoESQHtaCoR6jHjg7bNIwM4VkmKHL5cM5TQ32CHDh6Bcrki1sK4yO8PDmM5GMKxlMs8cim2v0hruhZKduwWO7RmiFIH+EL3Ydf7kNZxhDnUVFqCm+cUC4GP+1aEjlCjNO0zND5tMUdiWmOz/tTToTw/h6m0fZG2vZVQOnhKOdISa5MC+vN5KaR7Z8SWGw1cE3gKrTNzA2xzIrSynhTWZNPlC/uviO4zl9b6+L5tU62FKlwQYPvjCAc3EL+t0y159ASOh5wXOeqomMY9EnOCU75EtDaJdapM/DYR8yXjPlsG+gWkUCgUir5AX0AKhUKh6Av0BaRQKBSKvmDVakDNetU4T1mXp2JdQUxrDGIiwQNh0e6Sr5oJyEuNUgksiLU/C5T6YJZsyMNhex7HIy840iCk5uDTcQNan5OSqCU1FMougamxjTFTU1bLYd3GIf1LerR5OY/qkCNu8Vof0RUu8eEO2dp3xBjUKc25Q230RT8hk27MC1/6s1C+818+iW0WmhavewhJG2iJ9BgNutawgNrZqFi31YjxdqmWS1D2yBJfanYd4tYDSnHRcGyZlu6YyGD7pbeXRxpJROnIe/h+MdYJaT4uaaY1odkdWkRds0ljFwndarCI/TAwiOklnnhgN5RDoesGdD0epfM2oVhXNoL7/u9DB/C3wttxktZsvfrCHVB2PLyeVOigxRDHanQCryfr2H7rUEqLFs0veV/mSf91eQ1XiL+t1+3YZvQcWaihBuQJzS5q4/OJ1x464r4LPJf2pTlCv3XFeRLxbM5S1+BZnx76BaRQKBSKvkBfQAqFQqHoC1YtBddqZsaNn+ScXJFpL2D7/wTDJ2Xmz4AscVpkE1+i8qLIaFklm5u0QCGesT1PgWkoCuHO5Swl0Yk4wyDZzVPopRfYIeIspzkK5Y1Em9pEvbSJjvQELVUqYYgq/11Ckb0mFnSeR9Se7BdjjGk0LCVRreJ5OCNt1hGpGzJKFTCE9kBnXngZlMt7bVbNehPbMD5KFIqghIJB7MNqCakMX1A+WZ1SZeRx3NtNnot27HyiVxpVPJYj5kgaEV1H86klxqdK+6Z5smci+kXu3qZ7KSVabaZiKdMTFF4cV/Fa83l7fWefdRbUZWQXtOcRtCzKi3QZrTqFJlMYc07wqw7Z9qQuhro74t4JA8xafN4Zk1BOiNqvtu3cDCgMPqP7UCY17tD8z2iOJ+Jm8kgSqLdwTiQpZUAWNjgJWXotVZi0tn0eUDoSTrngCdoti4g4o/NEEaWXSJ4+BYOGYSsUCoViVUNfQAqFQqHoC/QFpFAoFIq+YNVqQEH65D9jjOmI1MENClENRzEksiF0BJPi+7WeIg8/b5BDXhA8druIXHp1Hq1ffMGrZpzuN0DOu922jY6IZ08ojDwjTaXVsqmOR0corXZ7+fTdLdYjOMS2bPUY1nESChk2xGNLXSdPYbPtFqaIrgsdIWlSSDClah4YlOl9sU0xhXevO/M8KO/b/b3u9pqY0mFQOoMB347ByDimhx5fi7ZEzbId91YFr602gHpF1GZrJHuecgXDc3M9aTjseGU0VibAPo4zO08T0ofKNCcM9VsmNJQ6zcVDR2dwX6FbpdSnE2vRyuaUUzd3tz0f77PHn3gcj4stNE3R5oDS2Tu01CB17K87LbaqoXkrwrun1mI/DEyiXhQ1SZ9sCiseSqngZXieSsWGqEektS4s4nOj2bLHLdBxPFo/0KlRunWhaVUo7UNCqU3ktXsFnj/0zIltm5OMl4GwlozPFbnEIRDt4+fYctAvIIVCoVD0BfoCUigUCkVfoC8ghUKhUPQFq1YDqi+1TPpU6mdPWIb4tHYhoth5Gfs/S9buZQf55aPEayfCon1mAfn9AqWaDgXP3SGetEVtMiLO3iU78zRjyxz8qUyrUC4jT822GFK7ySi1Ny2nMKFvtQNO1dDuWauE19NsWm66w3b5ZLdTq9myR3ZGxidrpEykSSB+PKX1CIURXMdx8Yt/sbv94De/AHU5srmXXvapg9pMGpOuIHQ1zkY8OoT6Y1KklO+OSCNCA9CJ8dr9nOX0TyxiH1aoTYkYuyb1aTsjzYQUl3bdaqQLlKLApX6SfbFpagrq1m1Yj/sKTbRB83/PQw/RcWktidA+Ek63EuE8lintezKx0FqeQKzrO20DpkzpRKivtGuYGiQVWk1IOlQnobU+UkNp43gM5Aq0r50jAaWOd2m9TsfhtBx2/6pH+lGIv/VFWhq+n1267+RjxDOU4p3kSGnbY4wxjtDkHDn3Mh6dp4d+ASkUCoWiL9AXkEKhUCj6glVLwYXeoMk99UnazixF5FGoZb2Bn6mlYKy7fayAIbUz9HmcmxqD8qI4VhhimKNhqqMhrHgoE2YtRlonFnYo+Tx+4uYoY2WS4nmkey5nTExpX0lK5PP46S9pM2PQUqNSYSse/MyuVNCeRqZbTIhuycjmIxO0IIdWZ0Q3SkoxR5RnaQnbOE7ZSN3Rdd3t6XOugLoDe+6A8pQYAv/EPNTl6U+ygZy9RWoNClGlaw3INbnRsBcow2+NMSamW6/csnOcabQO8bILdbtvg8KwmxRCz0xIK5Iht3jccQpJ37hhQ3eblxZERJHWhR/Nvn0HsK6OFC87pksujZ2bOSwb/2am7J0dvO9CYXVzyobNUJc2cU6za3i7ZvupQdxr5pJlTkO0o8MSAV27oMbjFJ9dMVnvJJQBec2opZ3vPXwC6uptsuIRWQF4qUdCVHIgsjB3yL07ddjtnjO82j6OBRWpVjwKhUKhWNXQF5BCoVAo+gJ9ASkUCoWiL1i1GlCWq5rsKQ43ENpANUE+sz46DeUjTcujzkaomTjDaOm/VGddxPKWnH00I73FF2GPdbKQdyirYEFk2UxIN2ANqLqEtvFS92Frd9aEQhES3aKUBJwRdUmeh47LaQU6VA5EFsSUUlGkpEE4gn92fGxDSNcu+WSSrMz8HPbLqVuQ0x8csyH07pnnQt3x/WgFc2TJ6j4BpcMokE4ViLyObg//TVb1dU59YK9nqYZ9HBuy9BeaSuaTFsCZMl1hTUVj45JFS4e0DXn7TE5hKPu69VjOeXZ8mNFPKA1EuWQH7NG9mG6B5CKTkQghNSGX7juet1ITjRycJPkAf+wI662tm/A54dJ9mNKzwhPaB4dsZy6NnUzBQGlEPB/LRaHNDpIeXG6Q1tRe3iIroMy9azfi2JXLts1Zi7K99ui0srzyNwk/g2QZxkqteBQKhUKxmqEvIIVCoVD0BfoCUigUCkVfsGo1oHDMNWH45PuxnVm+sxKhjfruKl7CvC848IzWzZCwwFbjPug8yJOGBeTlO2IdTUx2OkkbeVKZgmHN6CjUSasaY4wpUhoIaZPjkY0Pl6VNBnO1vA5Igi19uOzTeWJx7QFZyLvE/cpjsTlHkMPxqYtrjSn1755HHoHyjh0XQdkRY5AbQK3vip99JZTv/N//u7t94JHHoG6MUrFHTdumPM0JyqhsUlpvAW5IIbapTfY6cuwaxNHXaE1FW1jOpDRWTsr8PvbjGWdu626PTqCVkENrPlp1qy+1KNVEkzSgg/sPdLfrlHrdpfU6Hmmkcq56Hs6JmNovf+uRRU4c07oa8VOXUrO0apR6mjQg39gfe3nUKnkNVJaKZxD1/9g0rjVMxTOpSCndqxFprfR0jkS6bE5FMTCI8ysI7DOz08Hn09LSIpRTKQxSunGH7MpCWuvWFuu2XKmf9qxRfHroF5BCoVAo+gJ9ASkUCoWiL1i1FFzNHzbJU2Gux5v2c25vFT/tjscYythy7Sfi+CjWlRbx05MpIWlP4xC1kR/E8NaGyHDp03s8XyQHXEExlEWGTWN6Q3l7KLmcvQYvpLByors4Q6oE2+nIa+XQcLYAYcsf6Y6dss02hTFL+rFAmRmZFszlxOe9g6Oze/cDUM7Mr0FZ9lPEbt4D2MebLtnR3V637Wyoe3jX3VCuCaosZbqRJhA7m6di3NlJO+3JVGqvvZ6S+ziFukeeGB+izfJ0rdvPPg3KA0OWwm5GaN/CNkoyzN9PcezqZQyLP7h/nzwQ1KUphwFjx/ki7DylOZ3zl3eP53nLVLF0jy6XkN6aXI9UvuNTnwv7oDDHA01Fx/Z5YsiRe4DuWRHafgo5dJfo3g+I/vJa9liDRaK66dYPBD9M3WL8EGnBas0+y9pNkhOI6mOa0xGdgVmX1Q1boVAoFKsY+gJSKBQKRV+gLyCFQqFQ9AWrVgM6XC6Y/FNxiA8tzHX//yDpBqOTmKlxKLBhtItV1FtSsoKhiEOTCN6yWCBtiUIZA5GlNXBIxyFrnkLBtolDnDnbKIc5uiLslDWf2dlZ3FfoMQnx7L2pGyx6wrm5n+i88ljtCNsfUL+FQtdZqQ3cDjbyOHzkCJRjykqZikyOMruoMcZ0QjxvcdqmbohJr3vpf341lI88sb+7/b3voD7k0vWEeeonYYPDljhs19QS/HmVQujLDZxPg2M2fHrz+nVQNzaKodU+hTXXRWi14xFPT21KRRx5h3TBQ4ePQ7lZF6kQ2I7GewZ7FzG/2PKq0cL7vSgyBLcpbDlPKVSkhdfuhw9C3fjAVigXcqiH5aTuQ75cnov3qLTU8Tysy1OqlqIIl44yTB+xZmIYygvVEv62aI89xBpQme53ocX6PtkM0WO/MGDbzwlpU0pDU6OMx1IvrgktiTMyLwf9AlIoFApFX6AvIIVCoVD0BfoCUigUCkVfsGo1oPvLHRMET/KPt++y9u7TpyB3u2kIOdeK4ChTzlJLWgdb8QTGcqVeQlpNjFqHTE1baVH8fg51hZJcM0SvfE6pwHpLJnjsUhnX8vgBXrtcb9Soo/7lesuvz0ki5I87dUrHQDy85NYN2ekEnIpCcPYxpfvtRKjjZIJPTsmqprKI196kNg0Kq6RiDqe1S2tucnmrG5Yo9XeZOO/8ZrtOaGgBz/n47j1Qrs0tYJtE3yQxWcqE2KZS3drXDI+ircoFFz4PykWhW+XJOojX9nBKZRPY8YlJb2mR/VFTrAGZmcP59NjDaI2UCnsgQzpnwnnB2apfjHsQ0th5eC+lifgt9WmVUlzLVOb//G0cq4l1mL7gvM3Y5kHP9o03NIrNdVEoyXu2PLAG19j4BVxvJO/DqEpWYAGutTJ57Iu5Y6XudiFFrS9H3xKRSN0QJXicJMX7bs2I1c6aET7LQtJ0Jwbw+qRaOyHu2SSOTOn4XvNM0C8ghUKhUPQF+gJSKBQKRV+gLyCFQqFQ9AWrVgN68c4XmsJTNuiX7Lii+//5kbWw373Ew7ciqxWQtMHLE3q8o2QqhGoDY/TDELnQZkOkvCWOm9f2gMcciUD82zVr0B+q1RIpClK2tcf2z83YdUHchkIO258LhTbjIKftkG9ZzxoWoSuwZtWzjsm1U4x9pHiNSiy0gN46PE+JNKHRIctj5/JkrU+6lCv8uCbWosZw4vgclNuiz6dPPRPqHt+Pa5Oa89imPXse7W6PT4xD3eQUzuOJDRu62xvXT0Dd4BC20RMaS0Trc2LyD0t4vVRH+NPRaisnw7GrVazus/8JTGvebKAmJL0T2R6QU0DznEH/QLwfEkrxHov1eH6AJ+L1RvK3MzWcw9+462H8bX0UypsmbZsHA2xvcS2uvXJ8e56wSOvgQtZIxSOX9MexIuorQ7l5KKfpTHf70EF8PiWkUYe+1Z465BGZJ11H3nfDw/j8adP6R17HKH87MmLPyelUloN+ASkUCoWiL9AXkEKhUCj6glVLwW3atK4bbrrOsZ+Mt9+NtvyzJ05AWTIQqWErd/y8dykEutmxdIW02jEGM6AaY4wn0hUWKHVhtY7hurFMSUAh2kNDGHK7tIQ295KSoISbpl7Bz/BI2O8UCmhLEvfQaJZWaFN4dJvsjlzmVGQkbEwhqXmmGO02W4Iw/eiIcGlIzWCM6XQwvHh+vgTlTRum7b5EOTh5okUERZf6bEuC4xGLsN/byYrnazffAuU6pftwBAU0X8YsoVObtkC5KNJ9NIk+TUtIo+VE+oIO9b+fozQPlL3TE+OeUsbgiDL51muWMj129CjUOZQuIxM3Hkddc9g12+3ILKicYsEjWyhXUlh0bT3ZYB1pb4Rz4N92H4byC89DWi0YtmMQ5ilc2utQWWRpDbDOyxHNKWjzDlGgUYT3TjiJoeJh2V5f6xjeo60m0r+BWJbAWYu5/9viuTFQxDnhUiqQFi1/kFlQmy37PIpjpeAUCoVCsYqhLyCFQqFQ9AUn9QJKksS8//3vN1u3bjWFQsGcdtpp5g/+4A+ASsmyzHzgAx8w69atM4VCwezcudM89thjz3nDFQqFQvGjjZPSgP7oj/7IfOxjHzOf+MQnzDnnnGPuuece84Y3vMGMjIyYt771rcYYY/74j//YfPSjHzWf+MQnzNatW8373/9+87KXvczs2bPH5ImLXwnxU/+MMebocRt+uPfx/bCfS7qCIyxBXLKbjylVc0YceLttuXbHxa7h1Nly35Te4xyqKMsR252Q3rJS6gPmxzm9dyTaVCCbnjyVZervlNoUJxSWzckRxB8cHHbNuk6jYbWbjEKEmSceGLBcNV9rq4Xc+hFKB3DuWTb1tMuSFaeazuz1OJRKY900agF/8IE3d7fvJQ1ozTDarEQ0Z6Ru1SAb+/9989eh/Ku/+p+726Nk4e9SKHXcsuViATXFDqXHCCmEuC20m3Ybx7nZwn6anbFhwI0GztOMc4zDtZMIRP3fowmJOcPzP2ph6L5MGeGSzVBE8ykUaTlSBzXRdoDPotseRC15+zY7n3J5WlqQsKZi2x+3yfbGRS3ZL452t+sOPn+Kkxh+P7oFQ/evvMSGaV/0GjzubyxhH3/oj/5Hd/uJQ8egjlNryGdbpYa6chrj3OuF7Qv5bEtIm1wOJ/UC+s53vmNe8YpXmJe//OXGGGO2bNli/v7v/97cddddxpgnJ9INN9xgfu/3fs+84hWvMMYY88lPftJMTU2ZL3zhC+a1r31tzzHb7TY8zCuVSs8+CoVCofjxw0lRcM9//vPNLbfcYh599MkFdvfff7+57bbbzM/93M8ZY4zZv3+/mZmZMTt37uz+ZmRkxFx++eXmjjvueNpjXn/99WZkZKT7b9OmTd/vtSgUCoXiRwgn9QX0nve8x1QqFbN9+3bjeZ5JksR86EMfMldffbUxxpiZmSepsqkpzFI6NTXVrWO8973vNe94xzu65Uqloi8hhUKh+AnASb2APvvZz5pPfepT5tOf/rQ555xzzH333Weuu+46s379enPNNdd8Xw3I5XIml8v1/H+50TGdp/jFXfdb24xKlePskct1jOU3XVonUCDr+kYD+WXWbiQow7XxhTVPqVRa9nfG4FqZ0Ec+mbWOeh05WGPsNbikMbSbuK8n1uu4hmz4qf15sXaJ10+kIY5HSvU5wZ9L+tQYYxLSj6QVCcktxnHwPLIvXFq7kKP1U/NzuOYGZCpeiEJ2LoHopzCHc+Ltb38nlO+/937xOzxshdZsOdTneaHPRKTN8JqoL3zpq93tq1/7KqgbKeKc8UWKaJ6zRdI2OimtiRLraGLKv1yhVPKHjh7qbnM6CTeje0WMV8qeVw6v5cGxlToi2z4VijhHWmKNlEN2TbRkyPhi0nu0iC6mOXHvvkNQrkTWdmmti30akS4iJdQkwnnqRKjjbJq6qLu9+fRToS4xdN/xOq3Mjl3SoWdXHXWeV/zyK7rb/8+f3gh1QcgiqfP028YYj9JjxKQfdcT9LrVifq4th5N6Ab3zne8073nPe7paznnnnWcOHjxorr/+enPNNdeY6eknFwPOzs6adeusmDs7O2suuOCCkzmVQqFQKH7McVIaUKPR6PmLy/O8bqTW1q1bzfT0tLnlFrtCvFKpmDvvvNPs2LHjOWiuQqFQKH5ccFJfQL/4i79oPvShD5nNmzebc845x3zve98zf/Inf2Le+MY3GmOeDKG87rrrzB/+4R+abdu2dcOw169fb175yleeVMMOH18w+afcsA8fFa6wDtIRrRZl2RR2OkOD+DncbFKKVH7/ihDPzHA4NH/Ci/NylDLtK0Op2aWaQ9M5jFlSWhHZ0WzZjFrZwpx1cp49hp/kI4NoMSNptTDEfsryeEHSkdsYtGHxOcUrIRH9FHpIMTQaSPnIvuBMsUxhLSwg/dUS4bphQO7R1CZPjPv1f/CHUHfrLf8KZZmZtVDEUF5GjSM4RT/F7CJMdihXvvCF9jhEQ60ZxfNKqqnTRiomJMqEiZBOx/5Ph0Kpy7USlOtNHB9ARrSauD4O6+/JgEplSddwGHZMWXN9QekmRAMy7RMIl3c/Q7rRI/q3hlHmZt9Ba520bh06l0cZXt/0pm3d7YnN+If24MRGPI8I4W44w1DHlGJGlG4mqfAMZ/XAGsyQeta559hdHX4esYO6vZ4gYNd8vr/Jrqlu78s4EhmNkx9CGPaf/dmfmfe///3mzW9+szlx4oRZv369+a//9b+aD3zgA9193vWud5l6vW7e9KY3mVKpZF7wgheYr3/96ye1BkihUCgUP/44qRfQ0NCQueGGG8wNN9yw7D6O45gPfvCD5oMf/OAP2jaFQqFQ/BhDveAUCoVC0Res2nQMDzy43wRP2cdEwhI/ZVabuHSZuZTTMXAIoeuSriOsSdh6J6DQ5JawJuGQyIz48bbUJ4aR921SKoQWW49ky1vxVBuozQTCeuSUdagbjA7g3xrjov7gcczseegwZmL0i2g5I/WxtCfakrNsWl6bbYhk+gUuc4g8j0epvADlTmT7IiXr/Zjiv799+23iOGjBsuPiC6B8767d3e2E0lIElIEzoqyUnrCqd13sl4AsjPwBOy8cSqUxWyftb521bGGrlHaDrFMCnLex0FhaFFpdLuF5Og0ZX0w6Av/pKo7lsf0/p0GhKPlU/JaDnJKeY9n7IResnHoiEBY6rkv2Upz2wWD9vUfsWP7SBb8CdRs2n4IX4FrNkRyXzCxZGPk5Oxdd0kl6wshZXxX3h0salptSdtUJW3/ZZRdC3a3fRlOAQtHqw016pgzkRqHMlljghiTnCK9bWQb6BaRQKBSKvkBfQAqFQqHoC/QFpFAoFIq+YNVqQNVa0/jBkxypXIOTUDw/6wjFAcufV6qYBjmj9y3/NhD2NMxFV5ncNZLf55UmCGk1xOscPI91ELKqFykMOPV3mWx7BgatjrBxM1qAbNs0BuUXveiK7vbgKO77P//hS1D+t9t3QbnTEfmfyBKfJTpH6Ca9KbjNsuC1CpwVfGEBdapETGUnRD780AH0IbzjO/d0t6em1kPdUBH7dEfBHuvbd2I/DBdxvdGaNWugXKvYdBkkVZqJCVxbIse9WkcdJ42wTW2hCZ11OuoRrRrO0zppiqmwlWE7Gtbo4o6414jSd1xe/La8DQvrdz06zwq2LbSEBfSjlNZAsSCZxPY8GzdgP/3Wm38Lyv/ppT8N5ckNdl7UIzzPQoPsaNp2PHIB6ncurUlz4JHLaw2haNyUn1e27NNzI3Kwjfmc3fc3fv11UHfnHffieYw8Lo5V1JPChtcpPv0aLn6OLQf9AlIoFApFX6AvIIVCoVD0BauWgkvS1DhPfZN64hPeIS7Ac5fPaspZ+UKyd+mlhER4MX8PE2Q9H6dIli0Li9YWhy1mEqI9AnJJzmSoL4X5jg+h/YbnijalaFWz48oXQnnXU0kEjTFm9yOHoa5N7r9riaY6vN+GbXNILYcbyyyVDvFoGY1lItyZYxo7l2JUc3kMQ8082+a5JQx9/dKXboZyQThr58id/OzLzoTypZdbqvLY298LdW2iZedmkepLRCgqz5FaDcNd94m09aOjSOUVcjgnFiN7fXyc7WdsgXJM4xELp2p2v262yI9G7OsT/ctO2nKZQq8DN7a/J+OucHmPiI5zyFm7WLDjxZl63RzOry9/+Yvd7fPJDLlB9F1Ec3O2ZGlPppmZcvdFSL1Lx2GmMhG0p8v28LR8I2UXcXEwpqTzeaSdY/GsOGPb6VB3xmnboLz30X3dbXbrZ7d7z1v+m0W6oPc4oi8D/QJSKBQKRV+gLyCFQqFQ9AX6AlIoFApFX7BqNaA4Tbp+HzKMMyKrer9Atuola4nPoYDPlKVPnmdOpDYwppfDl1kcOZQ6JW3DFe3ISFviNnF9S3DVPvGvGVm0XHzeWd3tX/y5i6HuQmHPbowxS3OWh//i1+6BulqHOHoKJZVaWo3CfkPqC6nD5Ugb8wLiy0V4bmEQj1MqYdh1h2yVGi1bvvnmL0Mdp4MPBYe/bgOmjw9C1CsqzVJ3+8Uv+Rmo+8e//wf6Lc5FT4T5xzRvQ9L6GlWRyoEsZeZiLA8PW2ukfBHrShTC7QfI6ddF3oGIdLbFRbJgktprz/znNCJiWQKF8nL216jNGpH9bcjZeMnSxQuFXROlV/nqV3D5wOZtW7vbux97BOpOO2M7lNkSK4Nrh6qeVBqu2IFWdvRoZRJsK+bR4zigg6ViCUqWkl5E/SSfVy5pS1f/2q9B+fd/36YkSem+Mh5l+SWtqdWy800+E1l/Xw76BaRQKBSKvkBfQAqFQqHoC/QFpFAoFIq+YNVqQElm1wElIo01Z1btjVP3nnbbGFyX8XQoCf3IdVfuGmnjE5Ju0KY0wtJzhrWAHs6VINdAGQ/bP0Tpckdz9libxlHbOPAYalr37nq0u53LYYqIUgNTHVA3glbDmkmPRif0IrZgYesXySFzGvCA0gp4HmobX/3yv3S3m01cz/KCF6AedtZ2q4fd/8ADUDc6hmtwlpZK3e3zzjsP6v7p7/8RyoUCamWlmuxHHLuRYUxxsVlY6oytnYC6DZs2Q3n2hE0hceTwIaj711u/C+X/9LKdUK437PqwchlTiFfLqOdJqYPXh2QrOK34PmkXtKSuOIjzbSXbloTmfCb0O05pMTuPGlb2uJ1v42vxfnBJGxsknUqmUJFWYMZgOhJjUG+JM7auofTkAgG1IWBN1OPnlaxnGx+y9JL7kn53wQXnQnl03K4nlPPdGGM8TiXPaytFCniwNstWftb+O/QLSKFQKBR9gb6AFAqFQtEX6AtIoVAoFH3BqtWA4iju0ohSy2F+n1PEyn17+UpaY0DcrtQknmnNkDxP2uMpR+t1BAnOHnPMf6e0BkSmGc7aeO3bLjgVyi9/tV2n4o0jz37zP90C5e997+HutozlNwbt2Y3B9ONPttleL/PwzE1nwu+Kva8GBvC30uvKIw0uCFD7K+aHoPzEXqtpvWTnC6DusiuQ85ZrY7afg75YQ0PYb4mYIzf+2V9AXb2C6T6aZUybINd/xRHO0+IAzsUBsZ5txxWXQN2/3XE7lMfX2lQOV155JdRVF8tQPn4Mtb9Q+OBFtN6LdTW5TiuitUgOrfWR64R61t/RnGcPQKmPsVei55E+JMaD1yLNn8Brve+++7vbb3nrdVAX0PwKyWvQFW1mnTmme9QROkmSsAaE+0qdkPVs1p3ZV072Gz26UCs2mOY8o3Tj+UGce2ecfUZ3+44778Q2cPp0XgMlrl0Oe/YsP230C0ihUCgUfYG+gBQKhULRF6xaCq6TRMZ7iuoZLtpPxibZb6QU9ihpNKYC3ISyCEZIs8lPbQ7hXqnc7iC9kpDFRkdkFWQakCNQI6Jq2k0bGjuEX+xm27ZNUJ4+fUN3+4tfuQ3q7rh/Dx5XtCnqLB82bowxrsHPbk+EwqbUhxyfG4u+8fJI8XQoDHtw0IYmewH2Q4dSUczNI93ymlf/Unf7JTufj+3PE9UqijxWGdmfyBDb/Y8/AXWVxRKUpyen8TwdG8p7YvYo1DFVkxMWM2vGkAZcO4XZbLefbS2XZo6egLoWLQHg8yzO2TBs3+HQXbK9EaHJTOP4FH6fEUUnwSlGeI57gs7jFAu8rwz7TSNs701/+ZdQ/uM/+aPudrvFIeaUyoRDxcX1zR8/BnWDlAZFUuwJ3SuFPNpPyfufKTeOXGZLL8g4alYGPPtoZx7nX37VL3a3v3v3d6CObrseWWO5LKhqxaNQKBSKVQ19ASkUCoWiL9AXkEKhUCj6glWrAXmOa7ynwhBbTWkhj5x9q4OpdWVIJFuHd2LUHKoVtCLxQefBd7NDnuzSoSIi3p3bFIgQyQ5b0UdI0DrEted8e6J161ALuOLKF0H5e/c+3t2++eZ/g7oDBxehLHlrDnVNyeqdI2FlDGhA6ZajFlnxyNBq4sfjlPQjcZ4ejSSH+tHoKOokpwnr/TXjk1AXFvG39z+0u7udpxQR7Q62cWmu1N2uLWGIc4fC0+MErz2BtO143HIZj7VmbLS7Xa1g3cgQ2gMd2HdQHKcEdbU6hoZXWjjHAxGGvTCPlks+hVbnRCrwpIHj0aE5HnpW2+BQXU7P3GMwI9KMcNoTDvOPhHaZ83HfybVob7Rpgx3bZhvn/+FZbMOGSZwzRWH99NpfvgrqWi289k999jPd7c1bt0KdS6nMHZnOm8KseQkGOWDB3cO3JJelvtSbPgL3PU+kahkcwPthoV7CNpHN0qAIJW+JlO6ZpuRWKBQKxWqGvoAUCoVC0RfoC0ihUCgUfcGq1YCCoNBN5VutWk7c9/Gdmad00bHgkNMY961VS1B2SJNIEmmZwzY+yI2Wy3Y9Bdv2FIn3bQoefpCs6Ju0BqdINhlp2x77vAvRUmZhEddEffazN3e3DxxEkjtzUKtJBN/sOcizcx8zp98ROo8XrmzTL1n6lHS0oUHk7OU6Ap/6kMejWMRFUcNjdm1GWMQ5cfTIESiXha4zveEUqIsTvPb/989v7G4nnFY7j2PVIcuWipxvtI5sbg7X76zfZNd0xbSmJm6ibthqWg2CUzNvPfU0KJ99LqaQWJi3c/F7d2MqiuIg2ht1GvY8gU/pMFaw2+f7gecPr6mTdi68b9TB65O6bhpj+oV3/Z9vhvLxw1YTPX37pVDXpn47sO9xKI8KS6aFBbyXWg287/7owx/sbn/yU5/C8/BaHyHAJNyHbMtlCNLuiKp4bY88FqdBYZcxOV5XverVUPc3/98noMxzPA6e3Xqf5aBfQAqFQqHoC/QFpFAoFIq+YNVScLVqtevwKsOcyb2lx27HFyHPtVoJd6Ywx5TCgGUIaI6catmFW1pS+AFSCpzNMyfsQwLaN6FP9JE1aPPhJJZOWjuFVi8f/9vPQPmwCLX2AqRTMo8tZ2y/FQtIhdWb6OrMlEmQs79lFoFpKUmpuOQ4HOTYmsf2aUJjQ9GfZngEQ+yHRFg204CHDmDW0JGh0e72AFGrx+cwXPfAgcPd7SkK1a3W0N6lWsUQaLYtkWjTfJLJeg8dRtuecglDqaWL8ot+6qegbkiEcxtjzEIJQ7offdxSTWwh5REt5YqQ4YzoU4dskuF+8DmcG+cEU3QyE26D6C3OrhrH9lkwTM7lTzx+GMpnnm5pzSNPoI3SptPOgXK7gG185GFrXfXBD/4+1H3w//6/ofya17yqu83LKJj65lBrCY/CstmWaGUs77LvUhvY1srNbB/ffcc9uG8TH7gBUeNhaJ9P7aYdGylnrAT9AlIoFApFX6AvIIVCoVD0BfoCUigUCkVfsGo1oHarbtyntAdwFu9JkIhcdCg0lpDCiVtkE8N2L9I6hTMzRivx+a3lLWWMQXa21kTdwM/hEJRryPdffMH53e1v3fpdqHv8MdQ2nMzy2JnHVvtkr+MKq/2e0GnsU85oKcsh9ZOzgs7Wk/2VUiFIbaNcJpsk4p43bFgH5WER0l0m3ePoseNQPusMG87ukZXQI3sfg3K9brWaDWNroc5toyXL4AhqEvW6CC+OMXw1orn3zW/d2t0+9XQMpZ4YQyueiy69uLs9tg51qaOzGN599BjqSXfeYTNeOjTwXJYTmceOo34hfJr27ZDWFJImJA/l03ziVCDSA6tawz593+/9P1A+90xri/P2d74V6h4//A0on3XxDiifevrp3e1SqQR1//K//he2SWYCJR3H5T4VfcOB7AnrQ3wsOBGlzqDUGm0Qy7EN7TbOvXf+t3d3t2/+l5uhLlfAOT0+jnNx6YS1c1pasvop6+vLQb+AFAqFQtEX6AtIoVAoFH2BvoAUCoVC0ResWg2o046M+1Se3ECkK05T5D5Hh5GjrIm1GT00ZLIyb1oo2rUlHnHRccLahi13KEXESimIffJCTzzkY88+7Swol0vW8ufwwSWocyi+P5ezf090EjoPpSMfHMiLOuTofbLX4fUsksPvWalA/D/a6dPfO7QGqtGynL5DY5OQPc0ZZ5yBbRLHeviRvVDX6WD7U7G+JUd2QLfffgeUB0S6hkYbNcQipWau11nfs/0Uk+bj07U/8qBNEXHpxRdD3aWXXQLlDafY9S0hWRIdOnwQyhMjo1Cem7F6WMCWS6RlxsJ2xSFNka/HEakceN0Y60f5Aq7hkvcS3d7GJ12kKXS3kI4TU6qTh/dbq573/D7qQ+c8D++z23Y9AuWdL97Z3b7sihdC3S3fugXKV//6r4sS9qlnWMexSFhWewadbaWqmDShWBRbDdQq3/j634TyPd+9u7vNado7lN6jTOucZFqOStXqtpx+ZDnoF5BCoVAo+gJ9ASkUCoWiL1i1FFyWuSbLnno/ZiJkmMJZG/UWlW29S+9XtghhWq1QsOfh47r02ywT1iMeUlb5AGkRJ7DnidtowbJpeiOUhwvo5LzrHutY3Gkh5cCf7EPD9ryVKtIpSQf7otmU/YTUBX/Os3WKJ2hEtllhryQZzs4uz47D2SKf/nfGGJOlOO55Om95wYaDNipIGwQB7js6Md7dHhgehboHH9gNZVdcqxNiewuUPZL9gqR9k3SwNsYYlyiKxqIIOyeqj13bh4bsPGhSds4ztmAId62MtkpyfDhEuFFHG5xE7BtQf/tEsyVMHwkwHcNLGlK4DynzcEZjNyQyutbQDTvI4X3XENltRzyk6m+/61E6z/egfPHFl3e3v/I1DE1+wU9hJuLPfv7L3e1X/NIroS5n2MLITvKExpWXlLiGly2I4xAHF9FSiaPHrIP3b77+DVB38NH9UA7EjZfR2HAm4g4tI2m17ZxJxTZntl0O+gWkUCgUir5AX0AKhUKh6Av0BaRQKBSKvmDVakDtZrNrB5+llosuDqJGUq2h7YrMDJga5KkbFKY5sgZtJaqC3+TQUbZK9zyhDdB5WjXi3R3Lq4ZD2OWbTtsA5fvvfwjKzdjuHxb47wXUIGot26aU2p+kyO97QrdyfezTwRzqL/U6p2ew9e2I7ecptDezZYrwNClbwciUES7qTgM5DJeOWshFdyKrobgu8tZDwxNQltlUG5RSgbWlatXW5wZRY0gc5N196rdMpCwIKOXFGso+Wl60Ifa7H98HdS/82RdDWXL2ddIf10xOQfnv/uZPodxs2HspaaKu1gNha9UiO53Aw3ksbfrZij8cIO2VNCHP2GsITQnbkGLZF1rHoENaUoz3g1+U9yjN4QjnaUTz+KaPf7y7/Z9/9TVQVyji2OXE3Lz7nvug7oWXXwTljkgtw0s92Iondfl+t/OpQs+Y28im68P/l83SujSLWhkvR3HEfErpHuWxdGn5gHz2hTn7HMmy1HQaqHc/HfQLSKFQKBR9gb6AFAqFQtEX6AtIoVAoFH3BqtWATJZ28wRIK5gyWaOzF0wm1qzkaN1GjtaDRDGut5CWILxmiOPaXcHPxh3m0ombFmuGrrj0Uqjbvx9j8uu0FkNa0kS0xiYky5wgsOUsQ84+TynG5fXwuoxcHo/LfSE5Y14HxP3UFDYgYW55iyJjjAnC5Y/LrvysS8l1WZlhDybSHMQaln/56tegLo5Ivwgsry3XmBljzDClX8hSvJ7CgNUGHGrSUglTf3vCHujosWNQ127jeeUaqQEf+8kl3eArX8Prawsd1O9ZJ0cpocVYsl0T2zPJNjkuaaItbD812cSxHcsLzkcN60//9M1QXrt2rLvdrONYffFrt0L5pk/a9Tv7981CnWewEfkBnPOHDtn03ueccy7U3fS3N0H51a+5urv9j//4j1C3/dRTqP12DRrrtBl585yYmYPy7bff3t3+8pe/CnV3fgc1oFSMc0RrGkO6n6VlVMSp4mmcPY+shcR8k9ZgWZbS6sKnh34BKRQKhaIv0BeQQqFQKPoCfQEpFAqFoi9YtRpQp93s+iYNhjbunij6Hh0k9Sxvzdz5wDDuyzqCXPvD64DYz6pYtNpA1EGC36E1LBdd+Lzudo3WnRw9iimTc7TepdORKa2RW2e9RfLyBfKU47TIssz6EPuwcT/KvmGfONYgQMshAyvWlqR2Vqmin9vUGlzL0+s1ZccnR2nOHUrFXhXHvvVW1A3Yr84Vesb42DTU+QGOx2IT11s873kXdrfvueM7+NsQ+zgVvmVyTZAxxnikczbE2qS0iGtfHtz9IJ6HUoMUxf4x2fTnQtRFZFpnb4U1Kcagfiq1SGOMSRPytuN00q4d96t++SVQt2Eave3ygdWA8j7qaL/0i5jG4viM7cfPfOouqON7tlpD7SMs2us9chg1uT0PPgzlpZ32PBdTKo3Pf/FLUP7V1/5qd3t2fgHq/vnzuO9FF2Iajr//O6svPfA99K7LYry/U7Guifub71mpLfOzIO6w9odjKe9hedxnaQWnX0AKhUKh6A/0BaRQKBSKvmDVUnBhEHbpnEbDhia7ITcZ+Qlpn58r4Odki6zreykgcVSi4HjfWt1av8QUTnzu9m1Qzovw4zvvx09naWtjjOn5ds0E1RFTGPZKludMhXGZKbqV9u2l+qJl6zgbZrNpx65A2Ts5lDdfsL9lSxzel2lBOUfSlOcE267Y9u97AsPgwxDbmBOh4Q2yFvE5PQNl6HzwQUuHuRSazKk0ZJZQHpujIiTYGGOGRd/kJtdC3ecoDDija5epD3J0rRzmL8fWJ1rWo/suE0G3rotjl/PxPCn91vfs9R7YdwTqGh2kI3MDth8zsokZHT0VytIy52W/sAPqvvgFDE93PaK+xfz61Cf/J9S9+KU/C+V//qd/6m6/533vhbpj68ah/D//7hPd7Ucfx+y1F16I9N073nYdlMtLpe52m+ail1JYvHhe+USr9aRXWUF6YDo+pTTT8r6UIdrPMiGqfgEpFAqFoj/QF5BCoVAo+oJVR8H9+2d/lqbduKZMRNhklPkvTXjVuwXnaOR9nYz3WOG3Lv6PPFZKVABTZVEnEvtyeznrIdbjeWhf+lyW7rm8gjlJsMyf2rAv7trT5lS46TIF17Nvmixbxy1IxHH5U59/224xBWcpiWYDj9wiU96GiH7sbS/uK6+1pw9jdhVevi8yuh6OqpRlblOLVqdLt4yYoiojilriY8n7hzNw8r0l25QZpoaZghPH5XuUnCj4t6k4T7vNEYvs4m7HrkPRjYbo7HbL9gVHgXIbe65dtJkjv9o0oSRdV6tWoK5O4yPHskM0cquJ15rSfJNzaKX58+S+y49HzzNUlmme8g2x4hxJe///mTKjOtmzzZ36H4QjR46YTZs29bsZCoVCofgBcfjwYbNx48Zl61fdCyhNU3Ps2DGTZZnZvHmzOXz4sBkeHn7mH/6EolKpmE2bNmk/PQO0n54dtJ+eHbSfVkaWZaZarZr169f3BAFJrDoKznVds3HjRlOpPPkpOzw8rAP8LKD99Oyg/fTsoP307KD9tDxGRkaecR8NQlAoFApFX6AvIIVCoVD0Bav2BZTL5czv//7v9+aFUQC0n54dtJ+eHbSfnh20n54brLogBIVCoVD8ZGDVfgEpFAqF4scb+gJSKBQKRV+gLyCFQqFQ9AX6AlIoFApFX6AvIIVCoVD0Bav2BXTjjTeaLVu2mHw+by6//HJz1113PfOPfkxx/fXXm0svvdQMDQ2ZyclJ88pXvtLs3bsX9mm1Wubaa6814+PjZnBw0Fx11VVmdna2Ty1eHfjIRz5iHMcx1113Xff/tJ+exNGjR83rXvc6Mz4+bgqFgjnvvPPMPffc063Pssx84AMfMOvWrTOFQsHs3LnTPPbYY31s8X88kiQx73//+83WrVtNoVAwp512mvmDP/gDMNjUfvoBka1CfOYzn8nCMMz+5m/+JnvooYey//Jf/ks2Ojqazc7O9rtpfcHLXvay7Kabbsp2796d3XfffdnP//zPZ5s3b85qtVp3n9/6rd/KNm3alN1yyy3ZPffck11xxRXZ85///D62ur+46667si1btmTnn39+9ra3va37/9pPWba4uJidcsop2etf//rszjvvzPbt25fdfPPN2eOPP97d5yMf+Ug2MjKSfeELX8juv//+7Jd+6ZeyrVu3Zs1ms48t/4/Fhz70oWx8fDz7yle+ku3fvz/73Oc+lw0ODmb/43/8j+4+2k8/GFblC+iyyy7Lrr322m45SZJs/fr12fXXX9/HVq0enDhxIjPGZLfeemuWZVlWKpWyIAiyz33uc919Hn744cwYk91xxx39ambfUK1Ws23btmXf+MY3sp/6qZ/qvoC0n57Eu9/97uwFL3jBsvVpmmbT09PZf//v/737f6VSKcvlctnf//3f/0c0cVXg5S9/efbGN74R/u9Vr3pVdvXVV2dZpv30XGDVUXCdTsfs2rXL7Ny5s/t/ruuanTt3mjvuuKOPLVs9KJfLxhhjxsbGjDHG7Nq1y0RRBH22fft2s3nz5p/IPrv22mvNy1/+cugPY7Sf/h1f+tKXzCWXXGJe/epXm8nJSXPhhReav/7rv+7W79+/38zMzEA/jYyMmMsvv/wnqp+e//znm1tuucU8+uijxhhj7r//fnPbbbeZn/u5nzPGaD89F1h1btjz8/MmSRIzNTUF/z81NWUeeeSRPrVq9SBNU3PdddeZK6+80px77rnGGGNmZmZMGIZmdHQU9p2amjIzMzN9aGX/8JnPfMbce++95u677+6p0356Evv27TMf+9jHzDve8Q7zvve9z9x9993mrW99qwnD0FxzzTXdvni6e/AnqZ/e8573mEqlYrZv3248zzNJkpgPfehD5uqrrzbGGO2n5wCr7gWkWBnXXnut2b17t7ntttv63ZRVh8OHD5u3ve1t5hvf+IbJ5/P9bs6qRZqm5pJLLjEf/vCHjTHGXHjhhWb37t3mL/7iL8w111zT59atHnz2s581n/rUp8ynP/1pc84555j77rvPXHfddWb9+vXaT88RVh0FNzExYTzP64lMmp2dNdPT031q1erAW97yFvOVr3zFfOtb34Isg9PT06bT6ZhSqQT7/6T12a5du8yJEyfMRRddZHzfN77vm1tvvdV89KMfNb7vm6mpKe0nY8y6devM2WefDf931llnmUOHDhljTLcvftLvwXe+853mPe95j3nta19rzjvvPPPrv/7r5u1vf7u5/vrrjTHaT88FVt0LKAxDc/HFF5tbbrml+39pmppbbrnF7Nixo48t6x+yLDNvectbzOc//3nzzW9+02zduhXqL774YhMEAfTZ3r17zaFDh36i+uwlL3mJefDBB819993X/XfJJZeYq6++urut/WTMlVde2RPG/+ijj5pTTjnFGGPM1q1bzfT0NPRTpVIxd955509UPzUajZ5snp7nmTRNjTHaT88J+h0F8XT4zGc+k+Vyuexv//Zvsz179mRvetObstHR0WxmZqbfTesLfvu3fzsbGRnJ/vVf/zU7fvx491+j0eju81u/9VvZ5s2bs29+85vZPffck+3YsSPbsWNHH1u9OiCj4LJM+ynLngxR930/+9CHPpQ99thj2ac+9amsWCxmf/d3f9fd5yMf+Ug2OjqaffGLX8weeOCB7BWveMVPXHjxNddck23YsKEbhv3P//zP2cTERPaud72ru4/20w+GVfkCyrIs+7M/+7Ns8+bNWRiG2WWXXZZ997vf7XeT+gZjzNP+u+mmm7r7NJvN7M1vfnO2Zs2arFgsZr/8y7+cHT9+vH+NXiXgF5D205P48pe/nJ177rlZLpfLtm/fnv3VX/0V1Kdpmr3//e/Ppqamslwul73kJS/J9u7d26fW9geVSiV729velm3evDnL5/PZqaeemv3u7/5u1m63u/toP/1g0HxACoVCoegLVp0GpFAoFIqfDOgLSKFQKBR9gb6AFAqFQtEX6AtIoVAoFH2BvoAUCoVC0RfoC0ihUCgUfYG+gBQKhULRF+gLSKFQKBR9gb6AFAqFQtEX6AtIoVAoFH2BvoAUCoVC0Rf8/+3PqksdNVyIAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(samp[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "4b6d2ea3-92af-465c-9970-52394042d855",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "samp[2]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "382123fa",
   "metadata": {},
   "source": [
    "### Training and Testing Partition"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "8049ebcc-8923-4905-8c74-658908ef0068",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Creating the training and testing partition \n",
    "# train-partition\n",
    "train_data=data.take(round(len(data)*.7))\n",
    "train_data=train_data.batch(16) \n",
    "train_data=train_data.prefetch(8) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "f2cdf28d-3fbd-4b78-b675-1c9e8cde65ed",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_sample=train_data.as_numpy_iterator()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "08478eb8-b7dc-4bc5-8052-aa258437be9f",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_sample=train_sample.next()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "2e48f6e9-cc4e-4219-8ddf-f7bf791cb947",
   "metadata": {},
   "outputs": [],
   "source": [
    "# testing partition \n",
    "test_data=data.skip(round(len(data)*.7))\n",
    "test_data=test_data.take(round(len(data)*.3))\n",
    "test_data = test_data.batch(16)\n",
    "test_data = test_data.prefetch(8)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1c14d05e",
   "metadata": {},
   "source": [
    "# Building the Siamese Network\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cda7a635",
   "metadata": {},
   "source": [
    "### Building our Embedding Layer "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "4dea4577",
   "metadata": {},
   "outputs": [],
   "source": [
    "inp=Input(shape=(100,100,3),name='input_image')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "cf75db68",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<KerasTensor shape=(None, 100, 100, 3), dtype=float32, sparse=None, name=input_image>"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "inp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "72f289c8",
   "metadata": {},
   "outputs": [],
   "source": [
    "c1=Conv2D(64,(10,10),activation='relu')(inp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "599e4e53",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<KerasTensor shape=(None, 91, 91, 64), dtype=float32, sparse=False, name=keras_tensor>"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "c1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "faa285f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "m1 = MaxPooling2D(64, (2,2), padding='same')(c1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "09c5cdbf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<KerasTensor shape=(None, 46, 46, 64), dtype=float32, sparse=False, name=keras_tensor_1>"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "95a3557d",
   "metadata": {},
   "outputs": [],
   "source": [
    "c2 = Conv2D(128, (7,7), activation='relu')(m1)\n",
    "m2 = MaxPooling2D(64, (2,2), padding='same')(c2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "32edd8f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "c3 = Conv2D(128, (4,4), activation='relu')(m2)\n",
    "m3 = MaxPooling2D(64, (2,2), padding='same')(c3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "3526a40e",
   "metadata": {},
   "outputs": [],
   "source": [
    "c4 = Conv2D(256, (4,4), activation='relu')(m3)\n",
    "f1 = Flatten()(c4)\n",
    "d1 = Dense(4096, activation='sigmoid')(f1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "bda1a2ae",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "mod = Model(inputs=[inp], outputs=[d1], name='embedding')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "f01c2ce2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"embedding\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"embedding\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ input_image (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">91</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">91</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">19,264</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">46</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">46</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">40</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">40</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">401,536</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">20</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">20</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">17</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">17</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">262,272</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">9</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">9</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)      │       <span style=\"color: #00af00; text-decoration-color: #00af00\">524,544</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">9216</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4096</span>)           │    <span style=\"color: #00af00; text-decoration-color: #00af00\">37,752,832</span> │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ],
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ input_image (\u001b[38;5;33mInputLayer\u001b[0m)        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m91\u001b[0m, \u001b[38;5;34m91\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m19,264\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m46\u001b[0m, \u001b[38;5;34m46\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m40\u001b[0m, \u001b[38;5;34m40\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │       \u001b[38;5;34m401,536\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m20\u001b[0m, \u001b[38;5;34m20\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m17\u001b[0m, \u001b[38;5;34m17\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │       \u001b[38;5;34m262,272\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m9\u001b[0m, \u001b[38;5;34m9\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m256\u001b[0m)      │       \u001b[38;5;34m524,544\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ flatten (\u001b[38;5;33mFlatten\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m9216\u001b[0m)           │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4096\u001b[0m)           │    \u001b[38;5;34m37,752,832\u001b[0m │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">38,960,448</span> (148.62 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m38,960,448\u001b[0m (148.62 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">38,960,448</span> (148.62 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m38,960,448\u001b[0m (148.62 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "mod.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "e330f5d2",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "def make_embedding(): \n",
    "    inp = Input(shape=(100, 100, 3), name='input_image')\n",
    "    \n",
    "    # First block\n",
    "    c1 = Conv2D(64, (10, 10), activation='relu')(inp)\n",
    "    m1 = MaxPooling2D((2, 2), padding='same')(c1)\n",
    "    \n",
    "    # Second block\n",
    "    c2 = Conv2D(128, (7, 7), activation='relu')(m1)\n",
    "    m2 = MaxPooling2D((2, 2), padding='same')(c2)\n",
    "    \n",
    "    # Third block \n",
    "    c3 = Conv2D(128, (4, 4), activation='relu')(m2)\n",
    "    m3 = MaxPooling2D((2, 2), padding='same')(c3)\n",
    "    \n",
    "    # Final embedding block\n",
    "    c4 = Conv2D(256, (4, 4), activation='relu')(m3)\n",
    "    f1 = Flatten()(c4)\n",
    "    d1 = Dense(4096, activation='sigmoid')(f1)\n",
    "    \n",
    "    # Define the model\n",
    "    embedding_model = Model(inputs=inp, outputs=d1, name='embedding')\n",
    "    \n",
    "    return embedding_model\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "b19db3f0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"embedding\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"embedding\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ input_image (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">91</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">91</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">19,264</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">46</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">46</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">40</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">40</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">401,536</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">20</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">20</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">17</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">17</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">262,272</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">9</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">9</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)      │       <span style=\"color: #00af00; text-decoration-color: #00af00\">524,544</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">9216</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4096</span>)           │    <span style=\"color: #00af00; text-decoration-color: #00af00\">37,752,832</span> │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ],
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ input_image (\u001b[38;5;33mInputLayer\u001b[0m)        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m91\u001b[0m, \u001b[38;5;34m91\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m19,264\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m46\u001b[0m, \u001b[38;5;34m46\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m40\u001b[0m, \u001b[38;5;34m40\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │       \u001b[38;5;34m401,536\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m20\u001b[0m, \u001b[38;5;34m20\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m17\u001b[0m, \u001b[38;5;34m17\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │       \u001b[38;5;34m262,272\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m9\u001b[0m, \u001b[38;5;34m9\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m256\u001b[0m)      │       \u001b[38;5;34m524,544\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ flatten (\u001b[38;5;33mFlatten\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m9216\u001b[0m)           │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4096\u001b[0m)           │    \u001b[38;5;34m37,752,832\u001b[0m │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">38,960,448</span> (148.62 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m38,960,448\u001b[0m (148.62 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">38,960,448</span> (148.62 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m38,960,448\u001b[0m (148.62 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "embedding=make_embedding()\n",
    "embedding.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9fe91f7c",
   "metadata": {},
   "source": [
    "### Build Distance Layer "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "c5870cbd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Siamese L1 Distance class\n",
    "class L1Dist(Layer):\n",
    "    \n",
    "    # Init method - inheritance\n",
    "    def __init__(self, **kwargs):\n",
    "        super().__init__()\n",
    "       \n",
    "    # Magic happens here - similarity calculation\n",
    "    def call(self, inputs):\n",
    "        input_embedding,validation_embedding=inputs\n",
    "        return tf.abs(input_embedding - validation_embedding)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "2f35355a",
   "metadata": {},
   "outputs": [],
   "source": [
    "l1=L1Dist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "b9ffbcc5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<L1Dist name=l1_dist, built=False>"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "l1"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5be7c27c",
   "metadata": {},
   "source": [
    "### Make a Siamese Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "4618b8a2",
   "metadata": {},
   "outputs": [],
   "source": [
    "input_image = Input(name='input_img', shape=(100,100,3))\n",
    "validation_image = Input(name='validation_img', shape=(100,100,3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "4428d270",
   "metadata": {},
   "outputs": [],
   "source": [
    "inp_embedding = embedding(input_image)\n",
    "val_embedding = embedding(validation_image)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "3fc98f81",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<KerasTensor shape=(None, 4096), dtype=float32, sparse=False, name=keras_tensor_46>"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "inp_embedding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "77637405",
   "metadata": {},
   "outputs": [],
   "source": [
    "siamese_layer = L1Dist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "c555dcbe",
   "metadata": {},
   "outputs": [],
   "source": [
    "distances = siamese_layer([inp_embedding, val_embedding])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "4adf7080",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "siamese_model = make_siamese_model()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "1cdc38e8",
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_siamese_model(): \n",
    "    # Anchor image input in the network\n",
    "    input_image = Input(name='input_img', shape=(100,100,3))\n",
    "    \n",
    "    # Validation image in the network \n",
    "    validation_image = Input(name='validation_img', shape=(100,100,3))\n",
    "    \n",
    "    # Get embeddings for input and validation images\n",
    "    input_embedding = embedding(input_image)\n",
    "    validation_embedding = embedding(validation_image)\n",
    "    \n",
    "    # Combine siamese distance components\n",
    "    siamese_layer = L1Dist()\n",
    "    siamese_layer._name = 'distance'\n",
    "    distances = siamese_layer([input_embedding, validation_embedding])\n",
    "    \n",
    "    # Classification layer \n",
    "    classifier = Dense(1, activation='sigmoid')(distances)\n",
    "    \n",
    "    return Model(inputs=[input_image, validation_image], outputs=classifier, name='SiameseNetwork')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "db3d9a49",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "siamese_model = make_siamese_model()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "b8bb24ce",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"SiameseNetwork\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"SiameseNetwork\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)        </span>┃<span style=\"font-weight: bold\"> Output Shape      </span>┃<span style=\"font-weight: bold\">    Param # </span>┃<span style=\"font-weight: bold\"> Connected to      </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
       "│ input_img           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>,  │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ -                 │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)        │ <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)                │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ validation_img      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>,  │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ -                 │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)        │ <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)                │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ embedding           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4096</span>)      │ <span style=\"color: #00af00; text-decoration-color: #00af00\">38,960,448</span> │ input_img[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>],  │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Functional</span>)        │                   │            │ validation_img[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>… │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ l1_dist_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">L1Dist</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4096</span>)      │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ embedding[<span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>],  │\n",
       "│                     │                   │            │ embedding[<span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ dense_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)     │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)         │      <span style=\"color: #00af00; text-decoration-color: #00af00\">4,097</span> │ l1_dist_4[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]   │\n",
       "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n",
       "</pre>\n"
      ],
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape     \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m   Param #\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mConnected to     \u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
       "│ input_img           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m100\u001b[0m,  │          \u001b[38;5;34m0\u001b[0m │ -                 │\n",
       "│ (\u001b[38;5;33mInputLayer\u001b[0m)        │ \u001b[38;5;34m3\u001b[0m)                │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ validation_img      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m100\u001b[0m,  │          \u001b[38;5;34m0\u001b[0m │ -                 │\n",
       "│ (\u001b[38;5;33mInputLayer\u001b[0m)        │ \u001b[38;5;34m3\u001b[0m)                │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ embedding           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4096\u001b[0m)      │ \u001b[38;5;34m38,960,448\u001b[0m │ input_img[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m],  │\n",
       "│ (\u001b[38;5;33mFunctional\u001b[0m)        │                   │            │ validation_img[\u001b[38;5;34m0\u001b[0m… │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ l1_dist_4 (\u001b[38;5;33mL1Dist\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4096\u001b[0m)      │          \u001b[38;5;34m0\u001b[0m │ embedding[\u001b[38;5;34m4\u001b[0m][\u001b[38;5;34m0\u001b[0m],  │\n",
       "│                     │                   │            │ embedding[\u001b[38;5;34m5\u001b[0m][\u001b[38;5;34m0\u001b[0m]   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ dense_3 (\u001b[38;5;33mDense\u001b[0m)     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)         │      \u001b[38;5;34m4,097\u001b[0m │ l1_dist_4[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]   │\n",
       "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">38,964,545</span> (148.64 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m38,964,545\u001b[0m (148.64 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">38,964,545</span> (148.64 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m38,964,545\u001b[0m (148.64 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "siamese_model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b38cbf9f",
   "metadata": {},
   "source": [
    "## Training a Siamese Model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ffd8cc90",
   "metadata": {},
   "source": [
    "### Setup Loss and Optimizer "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "ad8bb4b5",
   "metadata": {},
   "outputs": [],
   "source": [
    "binary_cross_loss=tf.losses.BinaryCrossentropy()# that's how we set our loss function \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "656a3d17",
   "metadata": {},
   "outputs": [],
   "source": [
    "# define the optimsizer : We are going to use the Adam Optimizer here \n",
    "opt=tf.keras.optimizers.Adam(1e-4) # 0.0001\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bada4299",
   "metadata": {},
   "source": [
    "### Establish Checkpoints\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "1afecdb5",
   "metadata": {},
   "outputs": [],
   "source": [
    "checkpoint_dir='./training_checkpoints' # we are defining the checkpoint folder\n",
    "checkpoint_prefix=os.path.join(checkpoint_dir,'ckpt')\n",
    "checkpoint=tf.train.Checkpoint(siamese_model=siamese_model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b1f6ca3e",
   "metadata": {},
   "source": [
    "### Build Train Step Function "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f77ace94",
   "metadata": {},
   "source": [
    "The basic flow for training on one batch is as follows :\n",
    "1. Make Prediction \n",
    "2. Calculate loss\n",
    "3. Derive gradients\n",
    "4. Calculate new weights and apply "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "19779c0f",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "test_batch = train_data.as_numpy_iterator()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "7f8e1469",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "\n",
    "def resize_images(images):\n",
    "    # Ensure that the input tensor has 4 dimensions\n",
    "    if len(images.shape) == 1:\n",
    "        images = tf.expand_dims(images, axis=0)  # Add batch dimension\n",
    "    elif len(images.shape) == 3:\n",
    "        images = tf.expand_dims(images, axis=0)  # Add batch dimension\n",
    "        \n",
    "    # Resize the images\n",
    "    resized_images = tf.image.resize(images, (100, 100))\n",
    "    \n",
    "    # Ensure that the output tensor has 4 dimensions if the input tensor had 4 dimensions\n",
    "    if len(images.shape) == 4:\n",
    "        resized_images = tf.squeeze(resized_images, axis=0)  # Remove batch dimension if present\n",
    "    \n",
    "    return resized_images"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "e1cd54f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "@tf.function\n",
    "def train_step(batch):\n",
    "    \n",
    "    # Record all of our operations \n",
    "    with tf.GradientTape() as tape:     \n",
    "        # Get anchor and positive/negative image\n",
    "        X = batch[:2]\n",
    "        # Get label\n",
    "        y = batch[2]\n",
    "        \n",
    "        # Forward pass\n",
    "        yhat = siamese_model(X, training=True)\n",
    "        # Calculate loss\n",
    "        loss = binary_cross_loss(y, yhat)\n",
    "    print(loss)\n",
    "        \n",
    "    # Calculate gradients\n",
    "    grad = tape.gradient(loss, siamese_model.trainable_variables)\n",
    "    \n",
    "    # Calculate updated weights and apply to siamese model\n",
    "    opt.apply_gradients(zip(grad, siamese_model.trainable_variables))\n",
    "        \n",
    "    # Return loss\n",
    "    return loss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "fe030b4a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# so we are bulding the super resolution model \n",
    "# This function is focussed over one batch\n",
    "# we will wrap everything inside the @tf.function it compiles the function into the callable Tensorflow Graph\n",
    "@tf.function\n",
    "def train_step(batch):\n",
    "    \n",
    "    with tf.GradientTape() as tape:\n",
    "        X=resize_images(tf.convert_to_tensor(batch[:2])) # this gets the anchor and positive/negative imae \n",
    "        y=batch[2] # this gets the label\n",
    "        \n",
    "        # print(\"Shape of input images :\",X.shape)\n",
    "        # Forward Pass\n",
    "        yhat=siamese_model(X,training=True) \n",
    "        # super imp to set the training layer to true because certain layers are activated only when it's set to true \n",
    "        # calculate loss\n",
    "        loss=binary_cross_loss(y,yhat)\n",
    "        # Each batch in the dataset is compromised of 16 samples,each of which contains an anchor image,a positive or negative image and a label\n",
    "\n",
    "        # calculate gradients\n",
    "    grad=tape.gradient(loss,siamese_model.trainable_variables)\n",
    "        #calculate updated weights and apply to siamese model\n",
    "    opt.apply_gradients(zip(grad,siamese_model.trainable_variables))\n",
    "    return loss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "c076b67d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Exception ignored in: <bound method IPythonKernel._clean_thread_parent_frames of <ipykernel.ipkernel.IPythonKernel object at 0x0000019B2FA030A0>>\n",
      "Traceback (most recent call last):\n",
      "  File \"c:\\Users\\HP\\OneDrive\\Desktop\\M\\NND_Project\\NND_Project_Siamese_Neural_Network\\faceid\\lib\\site-packages\\ipykernel\\ipkernel.py\", line 770, in _clean_thread_parent_frames\n",
      "    def _clean_thread_parent_frames(\n",
      "KeyboardInterrupt: \n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1;31mInit signature:\u001b[0m\n",
      "\u001b[0mtf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlosses\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mBinaryCrossentropy\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m\n",
      "\u001b[0m    \u001b[0mfrom_logits\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m    \u001b[0mlabel_smoothing\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m    \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m    \u001b[0mreduction\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'sum_over_batch_size'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m    \u001b[0mname\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'binary_crossentropy'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mSource:\u001b[0m        \n",
      "\u001b[1;33m@\u001b[0m\u001b[0mkeras_export\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"keras.losses.BinaryCrossentropy\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\n",
      "\u001b[0m\u001b[1;32mclass\u001b[0m \u001b[0mBinaryCrossentropy\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mLossFunctionWrapper\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\n",
      "\u001b[0m    \u001b[1;34m\"\"\"Computes the cross-entropy loss between true labels and predicted labels.\n",
      "\n",
      "    Use this cross-entropy loss for binary (0 or 1) classification applications.\n",
      "    The loss function requires the following inputs:\n",
      "\n",
      "    - `y_true` (true label): This is either 0 or 1.\n",
      "    - `y_pred` (predicted value): This is the model's prediction, i.e, a single\n",
      "        floating-point value which either represents a\n",
      "        [logit](https://en.wikipedia.org/wiki/Logit), (i.e, value in [-inf, inf]\n",
      "        when `from_logits=True`) or a probability (i.e, value in [0., 1.] when\n",
      "        `from_logits=False`).\n",
      "\n",
      "    Args:\n",
      "        from_logits: Whether to interpret `y_pred` as a tensor of\n",
      "            [logit](https://en.wikipedia.org/wiki/Logit) values. By default, we\n",
      "            assume that `y_pred` is probabilities (i.e., values in [0, 1]).\n",
      "        label_smoothing: Float in range [0, 1]. When 0, no smoothing occurs.\n",
      "            When > 0, we compute the loss between the predicted labels\n",
      "            and a smoothed version of the true labels, where the smoothing\n",
      "            squeezes the labels towards 0.5. Larger values of\n",
      "            `label_smoothing` correspond to heavier smoothing.\n",
      "        axis: The axis along which to compute crossentropy (the features axis).\n",
      "            Defaults to `-1`.\n",
      "        reduction: Type of reduction to apply to the loss. In almost all cases\n",
      "            this should be `\"sum_over_batch_size\"`.\n",
      "            Supported options are `\"sum\"`, `\"sum_over_batch_size\"` or `None`.\n",
      "        name: Optional name for the loss instance.\n",
      "\n",
      "    Examples:\n",
      "\n",
      "    **Recommended Usage:** (set `from_logits=True`)\n",
      "\n",
      "    With `compile()` API:\n",
      "\n",
      "    ```python\n",
      "    model.compile(\n",
      "        loss=keras.losses.BinaryCrossentropy(from_logits=True),\n",
      "        ...\n",
      "    )\n",
      "    ```\n",
      "\n",
      "    As a standalone function:\n",
      "\n",
      "    >>> # Example 1: (batch_size = 1, number of samples = 4)\n",
      "    >>> y_true = [0, 1, 0, 0]\n",
      "    >>> y_pred = [-18.6, 0.51, 2.94, -12.8]\n",
      "    >>> bce = keras.losses.BinaryCrossentropy(from_logits=True)\n",
      "    >>> bce(y_true, y_pred)\n",
      "    0.865\n",
      "\n",
      "    >>> # Example 2: (batch_size = 2, number of samples = 4)\n",
      "    >>> y_true = [[0, 1], [0, 0]]\n",
      "    >>> y_pred = [[-18.6, 0.51], [2.94, -12.8]]\n",
      "    >>> # Using default 'auto'/'sum_over_batch_size' reduction type.\n",
      "    >>> bce = keras.losses.BinaryCrossentropy(from_logits=True)\n",
      "    >>> bce(y_true, y_pred)\n",
      "    0.865\n",
      "    >>> # Using 'sample_weight' attribute\n",
      "    >>> bce(y_true, y_pred, sample_weight=[0.8, 0.2])\n",
      "    0.243\n",
      "    >>> # Using 'sum' reduction` type.\n",
      "    >>> bce = keras.losses.BinaryCrossentropy(from_logits=True,\n",
      "    ...     reduction=\"sum\")\n",
      "    >>> bce(y_true, y_pred)\n",
      "    1.730\n",
      "    >>> # Using 'none' reduction type.\n",
      "    >>> bce = keras.losses.BinaryCrossentropy(from_logits=True,\n",
      "    ...     reduction=None)\n",
      "    >>> bce(y_true, y_pred)\n",
      "    array([0.235, 1.496], dtype=float32)\n",
      "\n",
      "    **Default Usage:** (set `from_logits=False`)\n",
      "\n",
      "    >>> # Make the following updates to the above \"Recommended Usage\" section\n",
      "    >>> # 1. Set `from_logits=False`\n",
      "    >>> keras.losses.BinaryCrossentropy() # OR ...('from_logits=False')\n",
      "    >>> # 2. Update `y_pred` to use probabilities instead of logits\n",
      "    >>> y_pred = [0.6, 0.3, 0.2, 0.8] # OR [[0.6, 0.3], [0.2, 0.8]]\n",
      "    \"\"\"\u001b[0m\u001b[1;33m\n",
      "\u001b[0m\u001b[1;33m\n",
      "\u001b[0m    \u001b[1;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[0mfrom_logits\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[0mlabel_smoothing\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[0mreduction\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"sum_over_batch_size\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[0mname\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"binary_crossentropy\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m    \u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[0msuper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m\n",
      "\u001b[0m            \u001b[0mbinary_crossentropy\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m            \u001b[0mname\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m            \u001b[0mreduction\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mreduction\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m            \u001b[0mfrom_logits\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfrom_logits\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m            \u001b[0mlabel_smoothing\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mlabel_smoothing\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m            \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[1;33m)\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfrom_logits\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mfrom_logits\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlabel_smoothing\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlabel_smoothing\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0maxis\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m\n",
      "\u001b[0m\u001b[1;33m\n",
      "\u001b[0m    \u001b[1;32mdef\u001b[0m \u001b[0mget_config\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[1;32mreturn\u001b[0m \u001b[1;33m{\u001b[0m\u001b[1;33m\n",
      "\u001b[0m            \u001b[1;34m\"name\"\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m            \u001b[1;34m\"reduction\"\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreduction\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m            \u001b[1;34m\"from_logits\"\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfrom_logits\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m            \u001b[1;34m\"label_smoothing\"\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlabel_smoothing\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m            \u001b[1;34m\"axis\"\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n",
      "\u001b[0m        \u001b[1;33m}\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mFile:\u001b[0m           c:\\users\\hp\\onedrive\\desktop\\m\\nnd_project\\nnd_project_siamese_neural_network\\faceid\\lib\\site-packages\\keras\\src\\losses\\losses.py\n",
      "\u001b[1;31mType:\u001b[0m           type\n",
      "\u001b[1;31mSubclasses:\u001b[0m     "
     ]
    }
   ],
   "source": [
    "tf.losses.BinaryCrossentropy??"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "20100fe7",
   "metadata": {},
   "source": [
    "### Building the Training Loop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a1707bc2",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "# Import metric calculations\n",
    "from tensorflow.keras.metrics import Precision, Recall\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "511da8d8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# This function over here is focussed over every batch in the dataset\n",
    "def train(data, EPOCHS):\n",
    "    for epoch in range(1, EPOCHS+1):\n",
    "        print('\\n Epoch {}/{}'.format(epoch, EPOCHS))\n",
    "        progbar = tf.keras.utils.Progbar(len(data))\n",
    "        \n",
    "        r = Recall()\n",
    "        p = Precision()\n",
    "        \n",
    "        for idx, batch in enumerate(data):\n",
    "            loss = train_step(batch)\n",
    "            yhat = siamese_model(resize_images(batch[:2]), training=False)\n",
    "            print(\"Shape of predicted outputs:\", yhat.shape)\n",
    "            r.update_state(batch[2], yhat)\n",
    "            p.update_state(batch[2], yhat) \n",
    "            progbar.update(idx+1)\n",
    "        print(loss.numpy(), r.result().numpy(), p.result().numpy())\n",
    "        \n",
    "        if epoch % 10 == 0: \n",
    "            checkpoint.save(file_prefix=checkpoint_prefix)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6636d9ad",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "def train(data, EPOCHS):\n",
    "    # Loop through epochs\n",
    "    for epoch in range(1, EPOCHS+1):\n",
    "        print('\\n Epoch {}/{}'.format(epoch, EPOCHS))\n",
    "        progbar = tf.keras.utils.Progbar(len(data))\n",
    "        \n",
    "        # Creating a metric object \n",
    "        r = Recall()\n",
    "        p = Precision()\n",
    "        \n",
    "        # Loop through each batch\n",
    "        for idx, batch in enumerate(data):\n",
    "            # Run train step here\n",
    "            loss = train_step(batch)\n",
    "            yhat = siamese_model.predict(batch[:2])\n",
    "            r.update_state(batch[2], yhat)\n",
    "            p.update_state(batch[2], yhat) \n",
    "            progbar.update(idx+1)\n",
    "        print(loss.numpy(), r.result().numpy(), p.result().numpy())\n",
    "        \n",
    "        # Save checkpoints\n",
    "        if epoch % 10 == 0: \n",
    "            checkpoint.save(file_prefix=checkpoint_prefix)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "810d1ca6",
   "metadata": {},
   "source": [
    "### Train the Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "14849542",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Epoch 1/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 6s/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2s/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 784ms/stepp\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepste\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepste\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 850ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 789ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 497ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 694ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 675ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 700ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 464ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 455ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 471ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 605ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 480ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 547ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 416ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 477ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 598ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 409ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 431ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 457ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 455ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 486ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 574ms/step\n",
      "\u001b[1m26/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m2s\u001b[0m 3s/stepTensor(\"binary_crossentropy/truediv:0\", shape=(), dtype=float32)\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2s/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m108s\u001b[0m 3s/step\n",
      "0.4446158 0.63316584 0.84\n",
      "\n",
      " Epoch 2/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 472ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 431ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 558ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 924ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 532ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 457ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 522ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 359ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 329ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 308ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 422ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 330ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 393ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 636ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 531ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 656ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 375ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 411ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 426ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 475ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 472ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 394ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 420ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 403ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 366ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 379ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 153ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m80s\u001b[0m 3s/step\n",
      "0.20683208 0.9317073 0.96954316\n",
      "\n",
      " Epoch 3/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 471ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 393ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 381ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 512ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 382ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 399ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 391ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 435ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 406ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 419ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 545ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 437ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 398ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 488ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 457ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 437ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 460ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 414ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 472ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 398ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 441ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 470ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 415ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 443ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 480ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 413ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 141ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m58s\u001b[0m 2s/step\n",
      "0.026559439 0.99523807 0.99523807\n",
      "\n",
      " Epoch 4/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 427ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 471ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 425ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 449ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 446ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 394ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 457ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 480ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 438ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 464ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 483ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 422ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 448ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 450ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 437ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 658ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 709ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 602ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 600ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 667ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 535ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 540ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 546ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 506ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 618ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 826ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 246ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m65s\u001b[0m 2s/step\n",
      "0.00031519472 1.0 1.0\n",
      "\n",
      " Epoch 5/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 714ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 596ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 489ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 547ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 529ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 541ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 683ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 494ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 570ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 532ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 497ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 491ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 545ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 519ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 649ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 495ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 531ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 490ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 508ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 523ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 483ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 549ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 558ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 204ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 2s/step\n",
      "0.0060765804 0.9952153 1.0\n",
      "\n",
      " Epoch 6/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 513ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 518ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 492ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 642ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 558ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 565ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 502ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 550ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 517ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 476ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 497ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 560ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 569ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 443ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 544ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 604ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 511ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 554ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 571ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 447ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 529ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 522ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 516ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 611ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 589ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 553ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 180ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m68s\u001b[0m 3s/step\n",
      "0.0007340121 1.0 1.0\n",
      "\n",
      " Epoch 7/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 544ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 682ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 514ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 473ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 500ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 565ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 550ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 512ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 503ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 486ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 508ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 586ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 541ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 625ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 570ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 514ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 466ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 570ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 507ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 567ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 471ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 524ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 538ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 145ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m68s\u001b[0m 3s/step\n",
      "0.00081163435 1.0 1.0\n",
      "\n",
      " Epoch 8/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 561ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 562ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 541ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 628ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 535ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 489ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 573ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 537ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 538ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 510ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 538ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 597ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 599ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 590ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 599ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 545ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 578ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 641ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 539ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 541ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 587ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 591ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 728ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 663ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 620ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 243ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 3s/step\n",
      "9.629681e-06 1.0 1.0\n",
      "\n",
      " Epoch 9/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 657ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 618ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 582ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 523ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 672ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 610ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 544ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 587ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 540ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 832ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 625ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 638ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 508ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 525ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 575ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 573ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 608ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 663ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 540ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 573ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 488ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 562ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 173ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 3s/step\n",
      "7.192387e-05 1.0 1.0\n",
      "\n",
      " Epoch 10/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 600ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 510ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 519ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 490ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 506ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 500ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 482ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 513ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 544ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 492ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 492ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 576ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 490ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 522ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 542ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 642ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 518ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 567ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 566ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 517ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 542ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 523ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 524ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 608ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 567ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 569ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 167ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m66s\u001b[0m 2s/step\n",
      "0.00010502715 1.0 1.0\n",
      "\n",
      " Epoch 11/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 473ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 659ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 487ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 626ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 837ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 883ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 914ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 618ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 560ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 609ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 627ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 649ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 814ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 846ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 683ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 619ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 684ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 634ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 624ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 729ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 943ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 700ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 809ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 583ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 205ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m91s\u001b[0m 3s/step\n",
      "1.3286057e-05 1.0 1.0\n",
      "\n",
      " Epoch 12/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 678ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 758ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 648ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 597ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 576ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 577ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 506ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 628ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 632ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 597ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 963ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 642ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 832ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 762ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 608ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 599ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 609ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 599ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 606ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 704ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 783ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 708ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 631ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 637ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 299ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m83s\u001b[0m 3s/step\n",
      "0.00034827675 1.0 1.0\n",
      "\n",
      " Epoch 13/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 557ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 846ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 734ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 635ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 794ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 507ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 641ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 546ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 556ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 592ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 531ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 997ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 707ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 638ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 531ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 678ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 497ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 501ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 493ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 505ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 571ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 624ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 723ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 489ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 3s/step\n",
      "7.656987e-05 1.0 1.0\n",
      "\n",
      " Epoch 14/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 542ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 504ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 616ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 502ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 503ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 523ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 564ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 593ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 635ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 516ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 504ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 643ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 923ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 586ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/step   \n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 649ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 497ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 445ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 482ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 527ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 777ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 428ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 529ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepe\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 3s/step\n",
      "0.00014342228 1.0 1.0\n",
      "\n",
      " Epoch 15/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 573ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 490ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 398ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 942ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 685ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 621ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 8s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 433ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 539ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 454ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 531ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 688ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 629ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 773ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 774ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 722ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 640ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 692ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 526ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 549ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 456ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 602ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 692ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 678ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 173ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m88s\u001b[0m 3s/step\n",
      "2.071577e-05 1.0 1.0\n",
      "\n",
      " Epoch 16/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 674ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 520ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 481ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 482ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 548ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 454ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 441ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 613ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 665ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 658ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 629ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 648ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 654ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 610ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 588ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 537ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 569ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 512ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 546ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 599ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 824ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 509ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 887ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 622ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 682ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 623ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 234ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 3s/step\n",
      "6.405159e-06 1.0 1.0\n",
      "\n",
      " Epoch 17/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 582ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 896ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 884ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/step   \n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 619ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 722ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 687ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 680ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 483ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 769ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 518ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 489ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 458ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 695ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 487ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 634ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 634ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 553ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 503ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 520ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 482ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 708ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 527ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 516ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 239ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 3s/step\n",
      "5.8198007e-06 1.0 1.0\n",
      "\n",
      " Epoch 18/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 709ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 713ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 590ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 597ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 740ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 716ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 646ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 546ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 590ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 479ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 652ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 561ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 509ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 616ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 655ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 559ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 540ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 598ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 542ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 591ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 524ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 584ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 829ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 518ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 625ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 341ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m76s\u001b[0m 3s/step\n",
      "1.0899472e-05 1.0 1.0\n",
      "\n",
      " Epoch 19/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 545ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 506ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 517ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 513ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 558ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 710ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 425ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 493ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 507ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 566ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 500ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 478ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 503ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 524ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 491ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 517ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 540ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 467ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 535ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 476ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 526ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 494ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 559ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 582ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 186ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 2s/step\n",
      "1.6451411e-05 1.0 1.0\n",
      "\n",
      " Epoch 20/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 482ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 568ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 523ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 482ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 514ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 491ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 553ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 594ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 541ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 573ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 789ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 635ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 648ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 615ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 699ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 828ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 686ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 638ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 523ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 589ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 985ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 698ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 723ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 593ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 629ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 262ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 3s/step\n",
      "0.0001985134 1.0 1.0\n",
      "\n",
      " Epoch 21/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 544ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 654ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 756ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 684ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 977ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 555ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 643ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 620ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 728ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 620ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 637ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 819ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 866ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 598ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 657ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 664ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 755ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 820ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 599ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 580ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 542ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 505ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 587ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 592ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 542ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 539ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m79s\u001b[0m 3s/step\n",
      "9.643132e-06 1.0 1.0\n",
      "\n",
      " Epoch 22/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 583ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 587ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 725ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 658ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 582ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 584ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 547ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 628ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 666ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 518ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 520ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 518ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 620ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 670ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 477ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 629ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 593ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 522ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 631ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 642ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 502ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 517ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 644ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 561ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 626ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 183ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 3s/step\n",
      "1.6803597e-05 1.0 1.0\n",
      "\n",
      " Epoch 23/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 537ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 541ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 526ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 486ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 529ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 621ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 496ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 524ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 705ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 681ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 536ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 633ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 604ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 746ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 621ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 573ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 649ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 628ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 546ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 561ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 653ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 641ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 651ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 267ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 3s/step\n",
      "0.00063149916 1.0 1.0\n",
      "\n",
      " Epoch 24/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 519ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 791ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 624ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 707ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 687ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 554ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 599ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 510ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 555ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 590ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 601ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 541ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 604ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 536ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 633ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 542ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 622ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 511ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 589ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 520ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 573ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 570ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 573ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 589ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 176ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 3s/step\n",
      "2.2261027e-06 1.0 1.0\n",
      "\n",
      " Epoch 25/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 670ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 766ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 622ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 654ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 613ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 672ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 612ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 614ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 549ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 527ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 542ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 576ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 512ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 577ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 639ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 620ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 573ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 734ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 779ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 480ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 528ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 532ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 543ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 519ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 571ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 677ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 212ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 3s/step\n",
      "7.948682e-06 1.0 1.0\n",
      "\n",
      " Epoch 26/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 772ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 512ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 540ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 581ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 611ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 530ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 634ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 563ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 556ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 529ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 481ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 545ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 615ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 621ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 499ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 545ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 548ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 559ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 496ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 643ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 527ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 571ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 488ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 537ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 191ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 3s/step\n",
      "3.64563e-07 1.0 1.0\n",
      "\n",
      " Epoch 27/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 786ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 868ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 713ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 842ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 8s/stepste\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepste\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 671ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 737ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 717ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2s/stepste\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepste\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 790ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepste\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 723ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 898ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepste\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 866ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 719ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 669ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 808ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 717ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 734ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 732ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 707ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 750ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 740ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 311ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m117s\u001b[0m 4s/step\n",
      "0.00010880719 1.0 1.0\n",
      "\n",
      " Epoch 28/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 802ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 856ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 742ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 677ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 689ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 717ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 851ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepste\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 813ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 734ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 665ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 676ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 661ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 670ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 716ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 634ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 767ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 724ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 727ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 901ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 723ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 778ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 654ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 616ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 282ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m94s\u001b[0m 3s/step\n",
      "3.8127334e-06 1.0 1.0\n",
      "\n",
      " Epoch 29/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 685ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 588ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 629ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 760ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 627ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 753ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 680ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 711ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 846ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 683ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 893ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 697ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 746ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 700ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 835ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 769ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 665ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 646ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 693ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 775ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 667ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 704ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 774ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 600ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 957ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 262ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m92s\u001b[0m 3s/step\n",
      "1.02559425e-05 1.0 1.0\n",
      "\n",
      " Epoch 30/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 726ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 677ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 660ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 713ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 665ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 746ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 982ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 981ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 628ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 622ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 700ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 719ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 630ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 837ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 704ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 630ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 602ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 597ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 698ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 645ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 658ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 784ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 728ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 649ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 730ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 872ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 251ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m86s\u001b[0m 3s/step\n",
      "1.2508175e-06 1.0 1.0\n",
      "\n",
      " Epoch 31/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/step   \n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 627ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 559ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 734ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 645ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 633ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 612ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 580ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 681ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 628ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 826ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 577ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 715ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 624ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 625ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 620ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 631ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 689ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 886ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 572ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 700ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 580ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 840ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 636ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 685ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 212ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m87s\u001b[0m 3s/step\n",
      "3.3503056e-06 1.0 1.0\n",
      "\n",
      " Epoch 32/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 677ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 618ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 931ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 795ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 936ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 657ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 890ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 759ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 648ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 724ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 706ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 654ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 885ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 710ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 716ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 485ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 707ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 665ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 692ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 511ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 512ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 477ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 517ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 553ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 442ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m84s\u001b[0m 3s/step\n",
      "0.00017004648 1.0 1.0\n",
      "\n",
      " Epoch 33/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 622ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 595ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 521ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 472ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 514ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 595ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 485ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 516ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 480ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 502ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 592ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 555ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 546ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 668ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 672ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 526ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 502ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 488ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 508ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 544ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 743ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 608ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 568ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 537ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 502ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 209ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 2s/step\n",
      "1.6816455e-07 1.0 1.0\n",
      "\n",
      " Epoch 34/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 645ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 546ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 637ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 599ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 558ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 542ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 554ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 695ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 807ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 669ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 528ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 529ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 535ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 556ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 497ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 496ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 552ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 496ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 762ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 696ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 713ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 623ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 708ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 764ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 201ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m78s\u001b[0m 3s/step\n",
      "8.1332195e-07 1.0 1.0\n",
      "\n",
      " Epoch 35/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 591ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 573ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 892ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 649ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 736ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 790ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 616ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 630ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 757ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 709ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 632ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 817ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 603ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 681ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 725ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 669ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 699ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 670ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 596ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 592ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 575ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 838ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 599ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 639ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 632ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 713ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 281ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m86s\u001b[0m 3s/step\n",
      "4.6964487e-06 1.0 1.0\n",
      "\n",
      " Epoch 36/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 651ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 899ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 662ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 688ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 910ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 636ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 640ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 700ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 729ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 651ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 737ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 720ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 633ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 698ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 583ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 662ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 603ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 635ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 572ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 553ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 844ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 713ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 622ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 633ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 940ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 583ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 397ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m85s\u001b[0m 3s/step\n",
      "3.0663764e-06 1.0 1.0\n",
      "\n",
      " Epoch 37/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 729ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 670ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 684ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 590ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 538ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 752ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 806ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 909ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 707ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 646ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 780ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 630ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 618ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 624ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 848ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 954ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 617ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 572ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 615ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 570ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 697ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 519ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 570ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 554ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 618ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 620ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 229ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 3s/step\n",
      "0.00011531606 1.0 1.0\n",
      "\n",
      " Epoch 38/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 629ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 742ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 638ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 503ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 696ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 587ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 545ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 669ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 516ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 490ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 548ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 520ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 506ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 478ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 509ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 502ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 521ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 521ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 554ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 550ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 957ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 609ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 615ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 600ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 572ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 618ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 193ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 3s/step\n",
      "3.8610747e-06 1.0 1.0\n",
      "\n",
      " Epoch 39/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 561ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 629ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 631ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 713ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 616ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 919ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 475ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 514ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 798ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 760ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 685ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 572ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 588ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 569ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 556ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 608ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 563ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 566ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 550ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 555ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 537ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 171ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m79s\u001b[0m 3s/step\n",
      "6.136143e-05 1.0 1.0\n",
      "\n",
      " Epoch 40/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 540ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 539ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 549ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 568ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 506ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 558ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 524ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 553ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 530ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 549ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 505ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 555ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 522ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 547ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 528ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 499ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 558ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 585ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 478ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 563ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 577ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 152ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 2s/step\n",
      "5.9105165e-05 1.0 1.0\n",
      "\n",
      " Epoch 41/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 510ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 546ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 505ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 550ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 507ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 530ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 495ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 546ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 541ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 481ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 517ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 538ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 519ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 476ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 544ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 535ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 555ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 538ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 509ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 528ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 493ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 484ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 157ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m66s\u001b[0m 2s/step\n",
      "5.453947e-05 1.0 1.0\n",
      "\n",
      " Epoch 42/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 518ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 525ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 498ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 510ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 541ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 505ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 557ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 625ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 696ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 526ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 530ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 548ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 545ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 684ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 492ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 530ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 520ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 502ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 535ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 522ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 477ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 520ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 517ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 484ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 517ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 185ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m66s\u001b[0m 2s/step\n",
      "5.4176973e-05 1.0 1.0\n",
      "\n",
      " Epoch 43/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 493ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 507ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 467ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 559ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 505ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 542ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 505ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 494ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 603ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 579ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 670ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 508ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 522ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 493ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 490ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 955ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 512ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/stepte\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 490ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 448ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 485ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 464ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 476ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 488ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 158ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m66s\u001b[0m 2s/step\n",
      "3.5675228e-05 1.0 1.0\n",
      "\n",
      " Epoch 44/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 495ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 459ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 624ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 525ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 475ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 474ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 408ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 439ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 478ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 441ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 634ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 734ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 464ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 576ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 659ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 480ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 505ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 491ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 493ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 624ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 528ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 500ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 469ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 502ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 529ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 557ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m62s\u001b[0m 2s/step\n",
      "2.1133926e-06 1.0 1.0\n",
      "\n",
      " Epoch 45/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 497ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 600ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 518ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 463ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 517ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 502ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 462ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 507ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 501ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 526ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 493ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 483ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 462ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 475ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 493ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 448ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 454ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 480ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 496ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 512ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 469ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 488ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 482ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 503ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 553ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 493ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 253ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m63s\u001b[0m 2s/step\n",
      "7.5755247e-07 1.0 1.0\n",
      "\n",
      " Epoch 46/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 464ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 703ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 505ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 495ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 441ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 650ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 487ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 561ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 546ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 448ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 551ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 585ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 571ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 860ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 714ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 522ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 483ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 536ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 582ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 559ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 557ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 576ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 492ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 510ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 180ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 2s/step\n",
      "8.8900464e-07 1.0 1.0\n",
      "\n",
      " Epoch 47/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 496ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 505ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 525ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 550ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 578ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 570ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 517ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 532ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 613ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 532ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 512ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 531ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 535ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 568ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 515ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 526ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 603ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 558ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 510ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 541ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 531ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 623ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 531ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 535ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 541ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 154ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 2s/step\n",
      "4.2376644e-08 1.0 1.0\n",
      "\n",
      " Epoch 48/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 512ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 488ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 499ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 572ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 480ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 501ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 525ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 518ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 591ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 511ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 508ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 511ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 506ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 540ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 535ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 499ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 547ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 491ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 528ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 559ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 476ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 468ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 518ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 528ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 577ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 472ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 193ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m65s\u001b[0m 2s/step\n",
      "2.6063622e-06 1.0 1.0\n",
      "\n",
      " Epoch 49/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 534ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 537ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 532ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 478ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 557ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 597ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 539ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 586ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 554ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 539ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 471ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 588ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 591ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 528ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 479ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 548ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 595ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 549ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 530ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 532ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 538ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 569ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 717ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 445ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 572ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 481ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 178ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 2s/step\n",
      "1.6727308e-05 1.0 1.0\n",
      "\n",
      " Epoch 50/50\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 671ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 670ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 529ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 616ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 692ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 713ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 647ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 553ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 540ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 542ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 493ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 666ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 499ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 626ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 673ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 742ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 529ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 708ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 589ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 631ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 537ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 554ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 583ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 555ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 513ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 537ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 238ms/step\n",
      "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m77s\u001b[0m 3s/step\n",
      "6.489736e-05 1.0 1.0\n"
     ]
    }
   ],
   "source": [
    "EPOCHS=50\n",
    "train(train_data,EPOCHS)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "006cba3a",
   "metadata": {},
   "source": [
    "## Evaluate Models"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "429f0266",
   "metadata": {},
   "source": [
    "### Import Metrics \n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "33256397",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "# Import metric calculations\n",
    "from tensorflow.keras.metrics import Precision, Recall"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b4c9bad5",
   "metadata": {},
   "source": [
    "### Make Predictions "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9cbafe9a",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "# Get a batch of test data\n",
    "test_input, test_val, y_true = test_data.as_numpy_iterator().next()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b16eaf65",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 8s/step\n"
     ]
    }
   ],
   "source": [
    "\n",
    "y_hat = siamese_model.predict([test_input, test_val])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2a50fb04",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1]"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Post processing the results \n",
    "[1 if prediction > 0.5 else 0 for prediction in y_hat ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dde182c6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0., 0., 1., 0., 0., 0., 1., 0., 0., 1., 0., 0., 0., 0., 0., 1.],\n",
       "      dtype=float32)"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_true"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2d7a20b4",
   "metadata": {},
   "source": [
    "### Calculate Metrics "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a3404f65",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Creating a metric object \n",
    "m = Recall()\n",
    "\n",
    "# Calculating the recall value \n",
    "m.update_state(y_true, y_hat)\n",
    "\n",
    "# Return Recall Result\n",
    "m.result().numpy()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f8b884fe",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Creating a metric object \n",
    "m = Precision()\n",
    "\n",
    "# Calculating the recall value \n",
    "m.update_state(y_true, y_hat)\n",
    "\n",
    "# Return Recall Result\n",
    "m.result().numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bce1b12c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2s/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2s/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 888ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 298ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 841ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 421ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 599ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 503ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 293ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 297ms/step\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 430ms/step\n",
      "1.0 1.0\n"
     ]
    }
   ],
   "source": [
    "r = Recall()\n",
    "p = Precision()\n",
    "# recall and precision being higher value is better \n",
    "for test_input, test_val, y_true in test_data.as_numpy_iterator():\n",
    "    yhat = siamese_model.predict([test_input, test_val])\n",
    "    r.update_state(y_true, yhat)\n",
    "    p.update_state(y_true,yhat) \n",
    "\n",
    "print(r.result().numpy(), p.result().numpy())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5bd1cca8",
   "metadata": {},
   "source": [
    "### Viz Results "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3b79cd53",
   "metadata": {},
   "source": [
    "\n",
    "plt.figure(figsize=(10,8))\n",
    "\n",
    "plt.subplot(1,2,1)\n",
    "plt.imshow(test_input[2])\n",
    "\n",
    "plt.subplot(1,2,2)\n",
    "plt.imshow(test_val[2])\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a42a1791",
   "metadata": {},
   "source": [
    "! Run This to Compare and Check the Results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "da4f7a44",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0., 1., 1., 1.], dtype=float32)"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_true"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "96d4c020",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[8.6772707e-12],\n",
       "       [3.5665093e-05],\n",
       "       [9.9999952e-01],\n",
       "       [1.2923982e-09],\n",
       "       [9.5273572e-12],\n",
       "       [5.3427623e-08],\n",
       "       [9.9999845e-01],\n",
       "       [8.3354657e-08],\n",
       "       [2.2545261e-09],\n",
       "       [1.0000000e+00],\n",
       "       [5.2568559e-14],\n",
       "       [2.6944114e-09],\n",
       "       [1.0700595e-12],\n",
       "       [3.5168418e-10],\n",
       "       [7.8178402e-07],\n",
       "       [9.9991447e-01]], dtype=float32)"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_hat"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4b40334",
   "metadata": {},
   "source": [
    "## Save the Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "428131f0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# siamese_model.save('siamese_model.h5')\n",
    "siamese_model.save('siamese_model.keras')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "babebd89",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "# Reload Model\n",
    "model = tf.keras.models.load_model('siamese_model.keras', custom_objects={'L1Dist': L1Dist})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "2d91ccfd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 7s/step\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[0.50093186],\n",
       "       [0.50093186],\n",
       "       [0.50093186],\n",
       "       [0.50093186]], dtype=float32)"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.predict([test_input,test_val])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "1a69c182",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"SiameseNetwork\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"SiameseNetwork\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)        </span>┃<span style=\"font-weight: bold\"> Output Shape      </span>┃<span style=\"font-weight: bold\">    Param # </span>┃<span style=\"font-weight: bold\"> Connected to      </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
       "│ input_img           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>,  │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ -                 │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)        │ <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)                │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ embedding           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4096</span>)      │ <span style=\"color: #00af00; text-decoration-color: #00af00\">38,960,448</span> │ input_img[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]   │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Functional</span>)        │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ l1_dist_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">L1Dist</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4096</span>)      │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ embedding[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>],  │\n",
       "│                     │                   │            │ embedding[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ validation_img      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>,  │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ -                 │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)        │ <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)                │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)     │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)         │      <span style=\"color: #00af00; text-decoration-color: #00af00\">4,097</span> │ l1_dist_2[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]   │\n",
       "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n",
       "</pre>\n"
      ],
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape     \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m   Param #\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mConnected to     \u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
       "│ input_img           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m100\u001b[0m,  │          \u001b[38;5;34m0\u001b[0m │ -                 │\n",
       "│ (\u001b[38;5;33mInputLayer\u001b[0m)        │ \u001b[38;5;34m3\u001b[0m)                │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ embedding           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4096\u001b[0m)      │ \u001b[38;5;34m38,960,448\u001b[0m │ input_img[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]   │\n",
       "│ (\u001b[38;5;33mFunctional\u001b[0m)        │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ l1_dist_2 (\u001b[38;5;33mL1Dist\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4096\u001b[0m)      │          \u001b[38;5;34m0\u001b[0m │ embedding[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m],  │\n",
       "│                     │                   │            │ embedding[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ validation_img      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m100\u001b[0m,  │          \u001b[38;5;34m0\u001b[0m │ -                 │\n",
       "│ (\u001b[38;5;33mInputLayer\u001b[0m)        │ \u001b[38;5;34m3\u001b[0m)                │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)         │      \u001b[38;5;34m4,097\u001b[0m │ l1_dist_2[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]   │\n",
       "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">38,964,545</span> (148.64 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m38,964,545\u001b[0m (148.64 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">38,964,545</span> (148.64 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m38,964,545\u001b[0m (148.64 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6ed88b86",
   "metadata": {},
   "source": [
    "## Real-Time Test"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a322006b",
   "metadata": {},
   "source": [
    "#### Verification Function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "1da90a08",
   "metadata": {},
   "outputs": [],
   "source": [
    "def verify(frame,model,detection_threshold,verification_threshold):\n",
    "    # build results array\n",
    "    results=[]\n",
    "    # looping through every image of the directory in verification_images\n",
    "    \n",
    "    for image in os.listdir(os.path.join('application_data','verification_images')):\n",
    "        input_img=preprocess(os.path.join('application_data','input_image','input_image.jpg'))\n",
    "        validation_img=preprocess(os.path.join('application_data','verification_images',image))\n",
    "        \n",
    "        result=model.predict(list(np.expand_dims([input_img,validation_img],axis=1)))\n",
    "        results.append(result)\n",
    "        \n",
    "    \n",
    "    detection=np.sum(np.array(results)>detection_threshold)\n",
    "    verification=detection/len(os.listdir(os.path.join('application_data','verification_images')))\n",
    "    verified=verification>verification_threshold\n",
    "    return results,verified\n",
    "# detection_threshold : metric over which the prediction is considered positive \n",
    "#verification threshold : proportion of positive predictions / positive samples \n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd2d7c22",
   "metadata": {},
   "source": [
    "### OpenCV Real Time Verification Images "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "40ce769b",
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'cv2' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[2], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m cap\u001b[38;5;241m=\u001b[39m\u001b[43mcv2\u001b[49m\u001b[38;5;241m.\u001b[39mVideoCapture(\u001b[38;5;241m0\u001b[39m)\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m cap\u001b[38;5;241m.\u001b[39misOpened():\n\u001b[0;32m      3\u001b[0m     ret,frame\u001b[38;5;241m=\u001b[39mcap\u001b[38;5;241m.\u001b[39mread()\n",
      "\u001b[1;31mNameError\u001b[0m: name 'cv2' is not defined"
     ]
    }
   ],
   "source": [
    "cap=cv2.VideoCapture(0)\n",
    "while cap.isOpened():\n",
    "    ret,frame=cap.read()\n",
    "    frame=frame[120:120+250,200:200+250,:]\n",
    "    cv2.imshow('Verification',frame)\n",
    "    \n",
    "    # verification trigger:\n",
    "    if cv2.waitKey(10) & 0xFF==ord('v'):\n",
    "        # Save the input image to input image folder \n",
    "        cv2.imwrite(os.path.join('application_data','input_image','input_image_jpg'),frame)\n",
    "        # verification image \n",
    "        results,verified=verify(frame,model,0.9,0.7)\n",
    "        print(verified)\n",
    "    \n",
    "    if cv2.waitKey(10) & 0xFF==ord('q'):\n",
    "        break\n",
    "cap.release()\n",
    "cv2.destroyAllWindows()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "48c05ad5",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.summary()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "faceid",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}