model_fe_too.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'0.25.3'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import math\n",
    "import sklearn\n",
    "import sklearn.preprocessing\n",
    "import os\n",
    "import h5py\n",
    "import matplotlib.pyplot as plt\n",
    "import tensorflow as tf\n",
    "import utils\n",
    "\n",
    "from tensorflow.keras.models import Model, Sequential\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "from tensorflow.keras.layers import LSTM, GRU, Bidirectional, Dense, Dropout, Input, TimeDistributed\n",
    "from tensorflow.keras.layers import Flatten, LeakyReLU, BatchNormalization\n",
    "from tensorflow.keras.callbacks import ModelCheckpoint\n",
    "from tensorflow.keras import backend as K\n",
    "\n",
    "tf.__version__\n",
    "pd.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['DJI_fe.csv',\n",
       " 'DJI_STO_20period_sma10.csv',\n",
       " 'N225.csv',\n",
       " 'DJI_modified_features - DJI.csv',\n",
       " 'N225fillVOL.csv',\n",
       " 'DJI_modified_sma.csv',\n",
       " 'downjone5y.csv',\n",
       " 'N225withoutNULL.csv',\n",
       " 'dowjone1985_2019.csv',\n",
       " '.ipynb_checkpoints',\n",
       " 'DJI_ema.csv',\n",
       " 'DJI_denoise.csv']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.listdir('./data')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# data stats parameter\n",
    "val_set_size_percentage = 10\n",
    "test_set_size_percentage = 10\n",
    "seq_len = 20\n",
    "\n",
    "# hyperparameter\n",
    "batch_size = 256\n",
    "epochs = 100\n",
    "lr = 1e-3\n",
    "decay = 1e-2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Date</th>\n",
       "      <th>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>Adj Close</th>\n",
       "      <th>Volume</th>\n",
       "      <th>sma_5</th>\n",
       "      <th>sma_10</th>\n",
       "      <th>sma_25</th>\n",
       "      <th>...</th>\n",
       "      <th>sma_125</th>\n",
       "      <th>sma_200</th>\n",
       "      <th>%K</th>\n",
       "      <th>%D</th>\n",
       "      <th>ema_5</th>\n",
       "      <th>ema_10</th>\n",
       "      <th>ema_25</th>\n",
       "      <th>ema_75</th>\n",
       "      <th>ema_125</th>\n",
       "      <th>ema_200</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1985-01-29</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1295.489990</td>\n",
       "      <td>1266.890015</td>\n",
       "      <td>1292.619995</td>\n",
       "      <td>1292.619995</td>\n",
       "      <td>13560000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1292.619995</td>\n",
       "      <td>1292.619995</td>\n",
       "      <td>1292.619995</td>\n",
       "      <td>1292.619995</td>\n",
       "      <td>1292.619995</td>\n",
       "      <td>1292.619995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1985-01-30</td>\n",
       "      <td>1297.369995</td>\n",
       "      <td>1305.099976</td>\n",
       "      <td>1278.930054</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>1287.880005</td>\n",
       "      <td>16820000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1291.039998</td>\n",
       "      <td>1291.758179</td>\n",
       "      <td>1292.255380</td>\n",
       "      <td>1292.495258</td>\n",
       "      <td>1292.544757</td>\n",
       "      <td>1292.572831</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1985-01-31</td>\n",
       "      <td>1283.239990</td>\n",
       "      <td>1293.400024</td>\n",
       "      <td>1272.640015</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>1286.770020</td>\n",
       "      <td>14070000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1289.616672</td>\n",
       "      <td>1290.851241</td>\n",
       "      <td>1291.833430</td>\n",
       "      <td>1292.344594</td>\n",
       "      <td>1292.453095</td>\n",
       "      <td>1292.515092</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1985-02-01</td>\n",
       "      <td>1276.939941</td>\n",
       "      <td>1286.109985</td>\n",
       "      <td>1269.770020</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>1277.719971</td>\n",
       "      <td>10980000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1285.651105</td>\n",
       "      <td>1288.463737</td>\n",
       "      <td>1290.747779</td>\n",
       "      <td>1291.959736</td>\n",
       "      <td>1292.219235</td>\n",
       "      <td>1292.367876</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1985-02-04</td>\n",
       "      <td>1272.079956</td>\n",
       "      <td>1294.939941</td>\n",
       "      <td>1268.989990</td>\n",
       "      <td>1290.079956</td>\n",
       "      <td>1290.079956</td>\n",
       "      <td>11630000</td>\n",
       "      <td>1287.013989</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1287.127389</td>\n",
       "      <td>1288.757595</td>\n",
       "      <td>1290.696408</td>\n",
       "      <td>1291.910268</td>\n",
       "      <td>1292.185279</td>\n",
       "      <td>1292.345111</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         Date         Open         High          Low        Close  \\\n",
       "0  1985-01-29  1277.719971  1295.489990  1266.890015  1292.619995   \n",
       "1  1985-01-30  1297.369995  1305.099976  1278.930054  1287.880005   \n",
       "2  1985-01-31  1283.239990  1293.400024  1272.640015  1286.770020   \n",
       "3  1985-02-01  1276.939941  1286.109985  1269.770020  1277.719971   \n",
       "4  1985-02-04  1272.079956  1294.939941  1268.989990  1290.079956   \n",
       "\n",
       "     Adj Close    Volume        sma_5  sma_10  sma_25  ...  sma_125  sma_200  \\\n",
       "0  1292.619995  13560000          NaN     NaN     NaN  ...      NaN      NaN   \n",
       "1  1287.880005  16820000          NaN     NaN     NaN  ...      NaN      NaN   \n",
       "2  1286.770020  14070000          NaN     NaN     NaN  ...      NaN      NaN   \n",
       "3  1277.719971  10980000          NaN     NaN     NaN  ...      NaN      NaN   \n",
       "4  1290.079956  11630000  1287.013989     NaN     NaN  ...      NaN      NaN   \n",
       "\n",
       "   %K  %D        ema_5       ema_10       ema_25       ema_75      ema_125  \\\n",
       "0 NaN NaN  1292.619995  1292.619995  1292.619995  1292.619995  1292.619995   \n",
       "1 NaN NaN  1291.039998  1291.758179  1292.255380  1292.495258  1292.544757   \n",
       "2 NaN NaN  1289.616672  1290.851241  1291.833430  1292.344594  1292.453095   \n",
       "3 NaN NaN  1285.651105  1288.463737  1290.747779  1291.959736  1292.219235   \n",
       "4 NaN NaN  1287.127389  1288.757595  1290.696408  1291.910268  1292.185279   \n",
       "\n",
       "       ema_200  \n",
       "0  1292.619995  \n",
       "1  1292.572831  \n",
       "2  1292.515092  \n",
       "3  1292.367876  \n",
       "4  1292.345111  \n",
       "\n",
       "[5 rows x 21 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('./data/DJI_fe.csv')\n",
    "df = df.drop('Unnamed: 0', axis=1)\n",
    "df = df.drop('Unnamed: 0.1', axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "utils.plot_raw(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Open', 'Close', 'High', 'Low', '%K', '%D', 'sma_5', 'ema_5', 'sma_10', 'ema_10', 'sma_25', 'ema_25', 'sma_75', 'ema_75', 'sma_125', 'ema_125', 'sma_200', 'ema_200']\n",
      "18\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/2two2/Documents/MultimodelStockPrediction/utils.py:44: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.\n",
      "  data_raw = stock.as_matrix()\n"
     ]
    }
   ],
   "source": [
    "df = df.dropna()\n",
    "df = df.drop('Date', axis=1)\n",
    "df = df.drop('Adj Close', axis=1)\n",
    "df = df.drop('Volume', axis=1)\n",
    "\n",
    "\n",
    "cols = ['Open', 'Close', 'High', 'Low', '%K', '%D']\n",
    "range_ma = [5, 10, 25, 75, 125, 200]\n",
    "for ma in range_ma:\n",
    "    cols.append('sma_' + str(ma))\n",
    "    cols.append('ema_' + str(ma))\n",
    "\n",
    "print(cols)\n",
    "print(len(cols))\n",
    "\n",
    "\n",
    "df_norm = utils.normalize_data(df,cols)\n",
    "\n",
    "x_train, y_train, x_val, y_val, x_test, y_test = utils.load_data(df_norm)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "x_train.shape =  (6835, 19, 18)\n",
      "y_train.shape =  (6835, 18)\n",
      "x_val.shape =  (854, 19, 18)\n",
      "y_val.shape =  (854, 18)\n",
      "x_test.shape =  (854, 19, 18)\n",
      "y_test.shape =  (854, 18)\n"
     ]
    }
   ],
   "source": [
    "print('x_train.shape = ', x_train.shape)\n",
    "print('y_train.shape = ', y_train.shape)\n",
    "print('x_val.shape = ', x_val.shape)\n",
    "print('y_val.shape = ', y_val.shape)\n",
    "print('x_test.shape = ', x_test.shape)\n",
    "print('y_test.shape = ', y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>sma_5</th>\n",
       "      <th>sma_10</th>\n",
       "      <th>sma_25</th>\n",
       "      <th>sma_75</th>\n",
       "      <th>sma_125</th>\n",
       "      <th>sma_200</th>\n",
       "      <th>%K</th>\n",
       "      <th>%D</th>\n",
       "      <th>ema_5</th>\n",
       "      <th>ema_10</th>\n",
       "      <th>ema_25</th>\n",
       "      <th>ema_75</th>\n",
       "      <th>ema_125</th>\n",
       "      <th>ema_200</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>199</th>\n",
       "      <td>0.000208</td>\n",
       "      <td>0.000243</td>\n",
       "      <td>0.000066</td>\n",
       "      <td>0.000226</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.874862</td>\n",
       "      <td>0.911597</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>200</th>\n",
       "      <td>0.000269</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000188</td>\n",
       "      <td>0.000202</td>\n",
       "      <td>0.000158</td>\n",
       "      <td>0.000044</td>\n",
       "      <td>0.000048</td>\n",
       "      <td>0.000027</td>\n",
       "      <td>0.815671</td>\n",
       "      <td>0.905829</td>\n",
       "      <td>0.000135</td>\n",
       "      <td>0.000172</td>\n",
       "      <td>0.000146</td>\n",
       "      <td>0.000082</td>\n",
       "      <td>0.000058</td>\n",
       "      <td>0.000042</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>201</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000155</td>\n",
       "      <td>0.000049</td>\n",
       "      <td>0.000442</td>\n",
       "      <td>0.000495</td>\n",
       "      <td>0.000453</td>\n",
       "      <td>0.000331</td>\n",
       "      <td>0.000093</td>\n",
       "      <td>0.000097</td>\n",
       "      <td>0.000058</td>\n",
       "      <td>0.930889</td>\n",
       "      <td>0.914344</td>\n",
       "      <td>0.000373</td>\n",
       "      <td>0.000393</td>\n",
       "      <td>0.000315</td>\n",
       "      <td>0.000174</td>\n",
       "      <td>0.000123</td>\n",
       "      <td>0.000088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>202</th>\n",
       "      <td>0.000389</td>\n",
       "      <td>0.000415</td>\n",
       "      <td>0.000244</td>\n",
       "      <td>0.000283</td>\n",
       "      <td>0.000732</td>\n",
       "      <td>0.000626</td>\n",
       "      <td>0.000479</td>\n",
       "      <td>0.000139</td>\n",
       "      <td>0.000138</td>\n",
       "      <td>0.000087</td>\n",
       "      <td>0.851183</td>\n",
       "      <td>0.902956</td>\n",
       "      <td>0.000478</td>\n",
       "      <td>0.000545</td>\n",
       "      <td>0.000459</td>\n",
       "      <td>0.000259</td>\n",
       "      <td>0.000184</td>\n",
       "      <td>0.000132</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>203</th>\n",
       "      <td>0.000292</td>\n",
       "      <td>0.000287</td>\n",
       "      <td>0.000111</td>\n",
       "      <td>0.000473</td>\n",
       "      <td>0.000795</td>\n",
       "      <td>0.000821</td>\n",
       "      <td>0.000612</td>\n",
       "      <td>0.000184</td>\n",
       "      <td>0.000180</td>\n",
       "      <td>0.000120</td>\n",
       "      <td>0.898578</td>\n",
       "      <td>0.903583</td>\n",
       "      <td>0.000612</td>\n",
       "      <td>0.000704</td>\n",
       "      <td>0.000606</td>\n",
       "      <td>0.000347</td>\n",
       "      <td>0.000248</td>\n",
       "      <td>0.000177</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Open      High       Low     Close     sma_5    sma_10    sma_25  \\\n",
       "199  0.000208  0.000243  0.000066  0.000226  0.000000  0.000000  0.000000   \n",
       "200  0.000269  0.000000  0.000000  0.000000  0.000188  0.000202  0.000158   \n",
       "201  0.000000  0.000155  0.000049  0.000442  0.000495  0.000453  0.000331   \n",
       "202  0.000389  0.000415  0.000244  0.000283  0.000732  0.000626  0.000479   \n",
       "203  0.000292  0.000287  0.000111  0.000473  0.000795  0.000821  0.000612   \n",
       "\n",
       "       sma_75   sma_125   sma_200        %K        %D     ema_5    ema_10  \\\n",
       "199  0.000000  0.000000  0.000000  0.874862  0.911597  0.000000  0.000000   \n",
       "200  0.000044  0.000048  0.000027  0.815671  0.905829  0.000135  0.000172   \n",
       "201  0.000093  0.000097  0.000058  0.930889  0.914344  0.000373  0.000393   \n",
       "202  0.000139  0.000138  0.000087  0.851183  0.902956  0.000478  0.000545   \n",
       "203  0.000184  0.000180  0.000120  0.898578  0.903583  0.000612  0.000704   \n",
       "\n",
       "       ema_25    ema_75   ema_125   ema_200  \n",
       "199  0.000000  0.000000  0.000000  0.000000  \n",
       "200  0.000146  0.000082  0.000058  0.000042  \n",
       "201  0.000315  0.000174  0.000123  0.000088  \n",
       "202  0.000459  0.000259  0.000184  0.000132  \n",
       "203  0.000606  0.000347  0.000248  0.000177  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "weight_path_model = \"saved_model/model_sma_ema_sto.h5\"\n",
    "callbacks_list_model = [\n",
    "    ModelCheckpoint(\n",
    "             weight_path_model,\n",
    "            save_best_only=True,\n",
    "            save_weights_only=True,\n",
    "            monitor='val_loss',\n",
    "            mode='min',\n",
    "            verbose=1\n",
    "        )\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"model\"\n",
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "input_1 (InputLayer)         [(None, 19, 18)]          0         \n",
      "_________________________________________________________________\n",
      "lstm (LSTM)                  (None, 19, 256)           281600    \n",
      "_________________________________________________________________\n",
      "time_distributed (TimeDistri (None, 19, 256)           0         \n",
      "_________________________________________________________________\n",
      "time_distributed_1 (TimeDist (None, 19, 256)           1024      \n",
      "_________________________________________________________________\n",
      "lstm_1 (LSTM)                (None, 128)               197120    \n",
      "_________________________________________________________________\n",
      "leaky_re_lu_1 (LeakyReLU)    (None, 128)               0         \n",
      "_________________________________________________________________\n",
      "batch_normalization_1 (Batch (None, 128)               512       \n",
      "_________________________________________________________________\n",
      "dense (Dense)                (None, 18)                2322      \n",
      "=================================================================\n",
      "Total params: 482,578\n",
      "Trainable params: 481,810\n",
      "Non-trainable params: 768\n",
      "_________________________________________________________________\n",
      "Train on 6835 samples, validate on 854 samples\n",
      "Epoch 1/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.2238 - mse: 0.2238\n",
      "Epoch 00001: val_loss improved from inf to 0.23716, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 20s 3ms/sample - loss: 0.2200 - mse: 0.2200 - val_loss: 0.2372 - val_mse: 0.2372\n",
      "Epoch 2/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0471 - mse: 0.0471\n",
      "Epoch 00002: val_loss improved from 0.23716 to 0.19921, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0468 - mse: 0.0468 - val_loss: 0.1992 - val_mse: 0.1992\n",
      "Epoch 3/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0252 - mse: 0.0252\n",
      "Epoch 00003: val_loss improved from 0.19921 to 0.17437, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0250 - mse: 0.0250 - val_loss: 0.1744 - val_mse: 0.1744\n",
      "Epoch 4/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0147 - mse: 0.0147\n",
      "Epoch 00004: val_loss improved from 0.17437 to 0.15729, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0147 - mse: 0.0147 - val_loss: 0.1573 - val_mse: 0.1573\n",
      "Epoch 5/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0090 - mse: 0.0090\n",
      "Epoch 00005: val_loss improved from 0.15729 to 0.14728, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0090 - mse: 0.0090 - val_loss: 0.1473 - val_mse: 0.1473\n",
      "Epoch 6/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0061 - mse: 0.0061\n",
      "Epoch 00006: val_loss improved from 0.14728 to 0.14151, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0061 - mse: 0.0061 - val_loss: 0.1415 - val_mse: 0.1415\n",
      "Epoch 7/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0048 - mse: 0.0048\n",
      "Epoch 00007: val_loss did not improve from 0.14151\n",
      "6835/6835 [==============================] - 14s 2ms/sample - loss: 0.0048 - mse: 0.0048 - val_loss: 0.1416 - val_mse: 0.1416\n",
      "Epoch 8/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0040 - mse: 0.0040\n",
      "Epoch 00008: val_loss improved from 0.14151 to 0.13726, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0040 - mse: 0.0040 - val_loss: 0.1373 - val_mse: 0.1373\n",
      "Epoch 9/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0035 - mse: 0.0035\n",
      "Epoch 00009: val_loss did not improve from 0.13726\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0035 - mse: 0.0035 - val_loss: 0.1374 - val_mse: 0.1374\n",
      "Epoch 10/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0033 - mse: 0.0033\n",
      "Epoch 00010: val_loss improved from 0.13726 to 0.12515, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 13s 2ms/sample - loss: 0.0033 - mse: 0.0033 - val_loss: 0.1251 - val_mse: 0.1251\n",
      "Epoch 11/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00011: val_loss improved from 0.12515 to 0.12008, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.1201 - val_mse: 0.1201\n",
      "Epoch 12/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0030 - mse: 0.0030\n",
      "Epoch 00012: val_loss improved from 0.12008 to 0.11476, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.1148 - val_mse: 0.1148\n",
      "Epoch 13/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0030 - mse: 0.0030\n",
      "Epoch 00013: val_loss improved from 0.11476 to 0.09899, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.0990 - val_mse: 0.0990\n",
      "Epoch 14/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0029 - mse: 0.0029\n",
      "Epoch 00014: val_loss improved from 0.09899 to 0.08793, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 2ms/sample - loss: 0.0029 - mse: 0.0029 - val_loss: 0.0879 - val_mse: 0.0879\n",
      "Epoch 15/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0030 - mse: 0.0030\n",
      "Epoch 00015: val_loss improved from 0.08793 to 0.07817, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 9s 1ms/sample - loss: 0.0030 - mse: 0.0030 - val_loss: 0.0782 - val_mse: 0.0782\n",
      "Epoch 16/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00016: val_loss improved from 0.07817 to 0.06697, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0670 - val_mse: 0.0670\n",
      "Epoch 17/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0027 - mse: 0.0027\n",
      "Epoch 00017: val_loss improved from 0.06697 to 0.05518, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0027 - mse: 0.0027 - val_loss: 0.0552 - val_mse: 0.0552\n",
      "Epoch 18/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00018: val_loss improved from 0.05518 to 0.03982, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 2ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0398 - val_mse: 0.0398\n",
      "Epoch 19/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0028 - mse: 0.0028\n",
      "Epoch 00019: val_loss improved from 0.03982 to 0.03280, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0028 - mse: 0.0028 - val_loss: 0.0328 - val_mse: 0.0328\n",
      "Epoch 20/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0025 - mse: 0.0025\n",
      "Epoch 00020: val_loss improved from 0.03280 to 0.02556, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0025 - mse: 0.0025 - val_loss: 0.0256 - val_mse: 0.0256\n",
      "Epoch 21/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0024 - mse: 0.0024\n",
      "Epoch 00021: val_loss improved from 0.02556 to 0.02172, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0024 - mse: 0.0024 - val_loss: 0.0217 - val_mse: 0.0217\n",
      "Epoch 22/100\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0025 - mse: 0.0025\n",
      "Epoch 00022: val_loss improved from 0.02172 to 0.01946, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0026 - mse: 0.0026 - val_loss: 0.0195 - val_mse: 0.0195\n",
      "Epoch 23/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0025 - mse: 0.0025\n",
      "Epoch 00023: val_loss improved from 0.01946 to 0.01313, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0025 - mse: 0.0025 - val_loss: 0.0131 - val_mse: 0.0131\n",
      "Epoch 24/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0024 - mse: 0.0024\n",
      "Epoch 00024: val_loss improved from 0.01313 to 0.01057, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0024 - mse: 0.0024 - val_loss: 0.0106 - val_mse: 0.0106\n",
      "Epoch 25/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0025 - mse: 0.0025\n",
      "Epoch 00025: val_loss improved from 0.01057 to 0.00859, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0025 - mse: 0.0025 - val_loss: 0.0086 - val_mse: 0.0086\n",
      "Epoch 26/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0024 - mse: 0.0024\n",
      "Epoch 00026: val_loss improved from 0.00859 to 0.00775, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0024 - mse: 0.0024 - val_loss: 0.0077 - val_mse: 0.0077\n",
      "Epoch 27/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0024 - mse: 0.0024\n",
      "Epoch 00027: val_loss improved from 0.00775 to 0.00617, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0024 - mse: 0.0024 - val_loss: 0.0062 - val_mse: 0.0062\n",
      "Epoch 28/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0024 - mse: 0.0024\n",
      "Epoch 00028: val_loss improved from 0.00617 to 0.00611, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0023 - mse: 0.0023 - val_loss: 0.0061 - val_mse: 0.0061\n",
      "Epoch 29/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0025 - mse: 0.0025\n",
      "Epoch 00029: val_loss did not improve from 0.00611\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0025 - mse: 0.0025 - val_loss: 0.0076 - val_mse: 0.0076\n",
      "Epoch 30/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0022 - mse: 0.0022\n",
      "Epoch 00030: val_loss improved from 0.00611 to 0.00586, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0022 - mse: 0.0022 - val_loss: 0.0059 - val_mse: 0.0059\n",
      "Epoch 31/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0022 - mse: 0.0022\n",
      "Epoch 00031: val_loss did not improve from 0.00586\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0022 - mse: 0.0022 - val_loss: 0.0072 - val_mse: 0.0072\n",
      "Epoch 32/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0023 - mse: 0.0023\n",
      "Epoch 00032: val_loss did not improve from 0.00586\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0023 - mse: 0.0023 - val_loss: 0.0069 - val_mse: 0.0069\n",
      "Epoch 33/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0022 - mse: 0.0022\n",
      "Epoch 00033: val_loss did not improve from 0.00586\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0022 - mse: 0.0022 - val_loss: 0.0063 - val_mse: 0.0063\n",
      "Epoch 34/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0023 - mse: 0.0023\n",
      "Epoch 00034: val_loss did not improve from 0.00586\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0023 - mse: 0.0023 - val_loss: 0.0071 - val_mse: 0.0071\n",
      "Epoch 35/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0021 - mse: 0.0021\n",
      "Epoch 00035: val_loss improved from 0.00586 to 0.00578, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0021 - mse: 0.0021 - val_loss: 0.0058 - val_mse: 0.0058\n",
      "Epoch 36/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0022 - mse: 0.0022\n",
      "Epoch 00036: val_loss did not improve from 0.00578\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0022 - mse: 0.0022 - val_loss: 0.0070 - val_mse: 0.0070\n",
      "Epoch 37/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0021 - mse: 0.0021\n",
      "Epoch 00037: val_loss improved from 0.00578 to 0.00528, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0021 - mse: 0.0021 - val_loss: 0.0053 - val_mse: 0.0053\n",
      "Epoch 38/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0021 - mse: 0.0021\n",
      "Epoch 00038: val_loss did not improve from 0.00528\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0021 - mse: 0.0021 - val_loss: 0.0060 - val_mse: 0.0060\n",
      "Epoch 39/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0021 - mse: 0.0021\n",
      "Epoch 00039: val_loss did not improve from 0.00528\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0021 - mse: 0.0021 - val_loss: 0.0053 - val_mse: 0.0053\n",
      "Epoch 40/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0022 - mse: 0.0022\n",
      "Epoch 00040: val_loss did not improve from 0.00528\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0022 - mse: 0.0022 - val_loss: 0.0059 - val_mse: 0.0059\n",
      "Epoch 41/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0021 - mse: 0.0021\n",
      "Epoch 00041: val_loss did not improve from 0.00528\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0021 - mse: 0.0021 - val_loss: 0.0053 - val_mse: 0.0053\n",
      "Epoch 42/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0022 - mse: 0.0022\n",
      "Epoch 00042: val_loss improved from 0.00528 to 0.00507, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0022 - mse: 0.0022 - val_loss: 0.0051 - val_mse: 0.0051\n",
      "Epoch 43/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0021 - mse: 0.0021\n",
      "Epoch 00043: val_loss improved from 0.00507 to 0.00494, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0021 - mse: 0.0021 - val_loss: 0.0049 - val_mse: 0.0049\n",
      "Epoch 44/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00044: val_loss did not improve from 0.00494\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0021 - mse: 0.0021 - val_loss: 0.0054 - val_mse: 0.0054\n",
      "Epoch 45/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0022 - mse: 0.0022\n",
      "Epoch 00045: val_loss did not improve from 0.00494\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0022 - mse: 0.0022 - val_loss: 0.0063 - val_mse: 0.0063\n",
      "Epoch 46/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00046: val_loss did not improve from 0.00494\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0020 - mse: 0.0020 - val_loss: 0.0052 - val_mse: 0.0052\n",
      "Epoch 47/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00047: val_loss did not improve from 0.00494\n",
      "6835/6835 [==============================] - 10s 2ms/sample - loss: 0.0020 - mse: 0.0020 - val_loss: 0.0050 - val_mse: 0.0050\n",
      "Epoch 48/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00048: val_loss improved from 0.00494 to 0.00473, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0020 - mse: 0.0020 - val_loss: 0.0047 - val_mse: 0.0047\n",
      "Epoch 49/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00049: val_loss did not improve from 0.00473\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0020 - mse: 0.0020 - val_loss: 0.0056 - val_mse: 0.0056\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 50/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0021 - mse: 0.0021\n",
      "Epoch 00050: val_loss did not improve from 0.00473\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0021 - mse: 0.0021 - val_loss: 0.0051 - val_mse: 0.0051\n",
      "Epoch 51/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00051: val_loss did not improve from 0.00473\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0020 - mse: 0.0020 - val_loss: 0.0051 - val_mse: 0.0051\n",
      "Epoch 52/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00052: val_loss did not improve from 0.00473\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0020 - mse: 0.0020 - val_loss: 0.0048 - val_mse: 0.0048\n",
      "Epoch 53/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00053: val_loss did not improve from 0.00473\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0020 - mse: 0.0020 - val_loss: 0.0050 - val_mse: 0.0050\n",
      "Epoch 54/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00054: val_loss did not improve from 0.00473\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0020 - mse: 0.0020 - val_loss: 0.0051 - val_mse: 0.0051\n",
      "Epoch 55/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0019 - mse: 0.0019\n",
      "Epoch 00055: val_loss did not improve from 0.00473\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0019 - mse: 0.0019 - val_loss: 0.0053 - val_mse: 0.0053\n",
      "Epoch 56/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0019 - mse: 0.0019\n",
      "Epoch 00056: val_loss did not improve from 0.00473\n",
      "6835/6835 [==============================] - 13s 2ms/sample - loss: 0.0019 - mse: 0.0019 - val_loss: 0.0050 - val_mse: 0.0050\n",
      "Epoch 57/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00057: val_loss did not improve from 0.00473\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0020 - mse: 0.0020 - val_loss: 0.0054 - val_mse: 0.0054\n",
      "Epoch 58/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0019 - mse: 0.0019\n",
      "Epoch 00058: val_loss improved from 0.00473 to 0.00461, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0019 - mse: 0.0019 - val_loss: 0.0046 - val_mse: 0.0046\n",
      "Epoch 59/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00059: val_loss did not improve from 0.00461\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0020 - mse: 0.0020 - val_loss: 0.0051 - val_mse: 0.0051\n",
      "Epoch 60/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00060: val_loss improved from 0.00461 to 0.00389, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0039 - val_mse: 0.0039\n",
      "Epoch 61/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0020 - mse: 0.0020\n",
      "Epoch 00061: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0020 - mse: 0.0020 - val_loss: 0.0049 - val_mse: 0.0049\n",
      "Epoch 62/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00062: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0047 - val_mse: 0.0047\n",
      "Epoch 63/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0019 - mse: 0.0019\n",
      "Epoch 00063: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 10s 2ms/sample - loss: 0.0019 - mse: 0.0019 - val_loss: 0.0048 - val_mse: 0.0048\n",
      "Epoch 64/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00064: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0048 - val_mse: 0.0048\n",
      "Epoch 65/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00065: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0057 - val_mse: 0.0057\n",
      "Epoch 66/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0019 - mse: 0.0019\n",
      "Epoch 00066: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0019 - mse: 0.0019 - val_loss: 0.0052 - val_mse: 0.0052\n",
      "Epoch 67/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00067: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 68/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0019 - mse: 0.0019\n",
      "Epoch 00068: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0019 - mse: 0.0019 - val_loss: 0.0055 - val_mse: 0.0055\n",
      "Epoch 69/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00069: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0047 - val_mse: 0.0047\n",
      "Epoch 70/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00070: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 71/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00071: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0046 - val_mse: 0.0046\n",
      "Epoch 72/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00072: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0048 - val_mse: 0.0048\n",
      "Epoch 73/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00073: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0040 - val_mse: 0.0040\n",
      "Epoch 74/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00074: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0044 - val_mse: 0.0044\n",
      "Epoch 75/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0019 - mse: 0.0019\n",
      "Epoch 00075: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0019 - mse: 0.0019 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 76/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0019 - mse: 0.0019\n",
      "Epoch 00076: val_loss did not improve from 0.00389\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 77/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00077: val_loss improved from 0.00389 to 0.00382, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0038 - val_mse: 0.0038\n",
      "Epoch 78/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00078: val_loss did not improve from 0.00382\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0046 - val_mse: 0.0046\n",
      "Epoch 79/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00079: val_loss did not improve from 0.00382\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0042 - val_mse: 0.0042\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 80/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00080: val_loss did not improve from 0.00382\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 81/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00081: val_loss did not improve from 0.00382\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0040 - val_mse: 0.0040\n",
      "Epoch 82/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00082: val_loss did not improve from 0.00382\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0046 - val_mse: 0.0046\n",
      "Epoch 83/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00083: val_loss improved from 0.00382 to 0.00361, saving model to saved_model/model_sma_ema_sto.h5\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0036 - val_mse: 0.0036\n",
      "Epoch 84/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00084: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0017 - mse: 0.0017 - val_loss: 0.0045 - val_mse: 0.0045\n",
      "Epoch 85/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00085: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 86/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00086: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 10s 2ms/sample - loss: 0.0017 - mse: 0.0017 - val_loss: 0.0040 - val_mse: 0.0040\n",
      "Epoch 87/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00087: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0017 - mse: 0.0017 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 88/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00088: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 89/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00089: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 9s 1ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0038 - val_mse: 0.0038\n",
      "Epoch 90/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00090: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 9s 1ms/sample - loss: 0.0017 - mse: 0.0017 - val_loss: 0.0039 - val_mse: 0.0039\n",
      "Epoch 91/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00091: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0043 - val_mse: 0.0043\n",
      "Epoch 92/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00092: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0017 - mse: 0.0017 - val_loss: 0.0038 - val_mse: 0.0038\n",
      "Epoch 93/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00093: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0038 - val_mse: 0.0038\n",
      "Epoch 94/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00094: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 10s 2ms/sample - loss: 0.0017 - mse: 0.0017 - val_loss: 0.0040 - val_mse: 0.0040\n",
      "Epoch 95/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00095: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0044 - val_mse: 0.0044\n",
      "Epoch 96/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0018 - mse: 0.0018\n",
      "Epoch 00096: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0018 - mse: 0.0018 - val_loss: 0.0044 - val_mse: 0.0044\n",
      "Epoch 97/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00097: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 11s 2ms/sample - loss: 0.0017 - mse: 0.0017 - val_loss: 0.0041 - val_mse: 0.0041\n",
      "Epoch 98/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00098: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0017 - mse: 0.0017 - val_loss: 0.0038 - val_mse: 0.0038\n",
      "Epoch 99/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00099: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 10s 1ms/sample - loss: 0.0017 - mse: 0.0017 - val_loss: 0.0036 - val_mse: 0.0036\n",
      "Epoch 100/100\n",
      "6656/6835 [============================>.] - ETA: 0s - loss: 0.0017 - mse: 0.0017\n",
      "Epoch 00100: val_loss did not improve from 0.00361\n",
      "6835/6835 [==============================] - 12s 2ms/sample - loss: 0.0017 - mse: 0.0017 - val_loss: 0.0043 - val_mse: 0.0043\n"
     ]
    }
   ],
   "source": [
    "K.clear_session()\n",
    "\n",
    "def get_bi_lstm():\n",
    "    \n",
    "    input1 = Input(shape=(19,18,))\n",
    "    x = LSTM(256, return_sequences=True)(input1)\n",
    "    x = TimeDistributed(LeakyReLU())(x)\n",
    "    x = TimeDistributed(BatchNormalization())(x)\n",
    "    x = LSTM(128)(x)\n",
    "    x =(LeakyReLU())(x)\n",
    "    x = (BatchNormalization())(x)\n",
    "    out = Dense(18,activation='linear')(x)\n",
    "\n",
    "    \n",
    "    \n",
    "    model = Model(inputs=input1, outputs=out)\n",
    "    model.summary()\n",
    "    model.compile(optimizer=Adam(learning_rate=lr, decay=decay),\n",
    "                loss='mse',\n",
    "                metrics=['mse'])   \n",
    "    \n",
    "    return model\n",
    "\n",
    "model = get_bi_lstm()\n",
    "\n",
    "history = model.fit(x_train, y_train, epochs=epochs,\n",
    "                   validation_data=(x_val, y_val), \n",
    "                   batch_size=batch_size, callbacks=callbacks_list_model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train_pred = model.predict(x_train)\n",
    "y_val_pred = model.predict(x_val)\n",
    "y_test_pred = model.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "utils.plot_result(y_train, y_val, y_test, y_train_pred, y_val_pred, y_test_pred, ft=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}