Model_2_on_Food_101_data.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "authorship_tag": "ABX9TyOh7tueNtoTS85Iy2MbQBqK",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/149189/Experiments_on_Food101_dataset/blob/main/Model_2_on_Food_101_data.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "OpIdQMNQvfgu"
      },
      "outputs": [],
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow.keras import layers, models\n",
        "import zipfile\n",
        "from pathlib import Path"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def unzip_data(zip_path, extract_to=\".\"):\n",
        "    with zipfile.ZipFile(zip_path, \"r\") as zip_ref:\n",
        "        zip_ref.extractall(extract_to)"
      ],
      "metadata": {
        "id": "k-ZsOI3bwQph"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!wget https://storage.googleapis.com/ztm_tf_course/food_vision/101_food_classes_10_percent.zip\n",
        "unzip_data(\"101_food_classes_10_percent.zip\")\n",
        "\n",
        "# Define paths\n",
        "train_dir = Path(\"101_food_classes_10_percent/train\")\n",
        "test_dir = Path(\"101_food_classes_10_percent/test\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "HpFN16agwT_H",
        "outputId": "cddaced2-dd9b-4942-93a6-3a7f0df6bf69"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2024-08-16 15:14:49--  https://storage.googleapis.com/ztm_tf_course/food_vision/101_food_classes_10_percent.zip\n",
            "Resolving storage.googleapis.com (storage.googleapis.com)... 74.125.137.207, 142.250.101.207, 142.251.2.207, ...\n",
            "Connecting to storage.googleapis.com (storage.googleapis.com)|74.125.137.207|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 1625420029 (1.5G) [application/zip]\n",
            "Saving to: ‘101_food_classes_10_percent.zip’\n",
            "\n",
            "101_food_classes_10 100%[===================>]   1.51G   133MB/s    in 19s     \n",
            "\n",
            "2024-08-16 15:15:08 (82.0 MB/s) - ‘101_food_classes_10_percent.zip’ saved [1625420029/1625420029]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "train_data = tf.keras.utils.image_dataset_from_directory(\n",
        "    train_dir,\n",
        "    image_size=(224, 224),\n",
        "    batch_size=32\n",
        ")\n",
        "\n",
        "test_data = tf.keras.utils.image_dataset_from_directory(\n",
        "    test_dir,\n",
        "    image_size=(224, 224),\n",
        "    batch_size=32\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vS_uSWv-wXGQ",
        "outputId": "c901d5e5-3a37-4251-d250-820559e74a51"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 7575 files belonging to 101 classes.\n",
            "Found 25250 files belonging to 101 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data_augmentation = tf.keras.Sequential([\n",
        "    layers.RandomFlip(\"horizontal_and_vertical\"),\n",
        "    layers.RandomRotation(0.2),\n",
        "    layers.RandomZoom(0.2),\n",
        "    layers.RandomHeight(0.1),\n",
        "    layers.RandomWidth(0.1),\n",
        "], name=\"data_augmentation\")"
      ],
      "metadata": {
        "id": "HMj-hxCpwZXA"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "base_model = tf.keras.applications.EfficientNetB0(include_top=False)\n",
        "base_model.trainable = False"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "x-Z2sxeUwbxS",
        "outputId": "005ff6fd-7460-4463-bfd0-010dbe17f03c"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://storage.googleapis.com/keras-applications/efficientnetb0_notop.h5\n",
            "\u001b[1m16705208/16705208\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "inputs = layers.Input(shape=(224, 224, 3), name=\"input_layer\")\n",
        "x = data_augmentation(inputs)\n",
        "x = base_model(x, training=False)\n",
        "x = layers.GlobalAveragePooling2D(name=\"global_average_pooling_layer\")(x)\n",
        "outputs = layers.Dense(101, activation=\"softmax\", name=\"output_layer\")(x)\n",
        "model = models.Model(inputs, outputs)"
      ],
      "metadata": {
        "id": "ZN6Vd9Bywdj_"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.compile(\n",
        "    loss=\"sparse_categorical_crossentropy\",\n",
        "    optimizer=tf.keras.optimizers.Adam(),\n",
        "    metrics=[\"accuracy\"]\n",
        ")"
      ],
      "metadata": {
        "id": "iO6ab18KwfpI"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=\"logs/feature_extraction\")\n",
        "checkpoint_callback = tf.keras.callbacks.ModelCheckpoint(\"best_model.keras\", save_best_only=True)"
      ],
      "metadata": {
        "id": "s0E3-XKrwjMA"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "history = model.fit(\n",
        "    train_data,\n",
        "    epochs=5,\n",
        "    validation_data=test_data,\n",
        "    validation_steps=int(0.25 * len(test_data)),\n",
        "    callbacks=[tensorboard_callback, checkpoint_callback]\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BW-keUxLwlkB",
        "outputId": "29f5a0c7-a057-436b-a13c-85fdcb2fbca5"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/5\n",
            "\u001b[1m237/237\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m52s\u001b[0m 216ms/step - accuracy: 0.1286 - loss: 4.0721 - val_accuracy: 0.4028 - val_loss: 2.6503\n",
            "Epoch 2/5\n",
            "\u001b[1m237/237\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m76s\u001b[0m 194ms/step - accuracy: 0.3993 - loss: 2.6746 - val_accuracy: 0.4613 - val_loss: 2.2271\n",
            "Epoch 3/5\n",
            "\u001b[1m237/237\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m79s\u001b[0m 183ms/step - accuracy: 0.4654 - loss: 2.2805 - val_accuracy: 0.5054 - val_loss: 2.0218\n",
            "Epoch 4/5\n",
            "\u001b[1m237/237\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 180ms/step - accuracy: 0.5051 - loss: 2.0763 - val_accuracy: 0.5044 - val_loss: 1.9515\n",
            "Epoch 5/5\n",
            "\u001b[1m237/237\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 115ms/step - accuracy: 0.5326 - loss: 1.9086"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/lib/python3.10/contextlib.py:153: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.\n",
            "  self.gen.throw(typ, value, traceback)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m237/237\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 128ms/step - accuracy: 0.5326 - loss: 1.9085 - val_accuracy: 0.4118 - val_loss: 2.4754\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "results_feature_extraction_model = model.evaluate(test_data)\n",
        "results_feature_extraction_model\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Mugvx2zXwo65",
        "outputId": "6d5bbb44-5c1f-4a22-d564-168c56283ff7"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m790/790\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m58s\u001b[0m 74ms/step - accuracy: 0.5124 - loss: 1.8918\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[1.8876498937606812, 0.5155247449874878]"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "!wget https://raw.githubusercontent.com/mrdbourke/tensorflow-deep-learning/main/extras/helper_functions.py"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ICRtWkkXylq5",
        "outputId": "e2cb35fc-e8ae-4cab-da7b-6e30eac7133f"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2024-08-16 15:25:55--  https://raw.githubusercontent.com/mrdbourke/tensorflow-deep-learning/main/extras/helper_functions.py\n",
            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 10246 (10K) [text/plain]\n",
            "Saving to: ‘helper_functions.py’\n",
            "\n",
            "\rhelper_functions.py   0%[                    ]       0  --.-KB/s               \rhelper_functions.py 100%[===================>]  10.01K  --.-KB/s    in 0s      \n",
            "\n",
            "2024-08-16 15:25:55 (118 MB/s) - ‘helper_functions.py’ saved [10246/10246]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from helper_functions import create_tensorboard_callback, plot_loss_curves, unzip_data"
      ],
      "metadata": {
        "id": "uPUXFbOcytBa"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "plot_loss_curves(history)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 927
        },
        "id": "BGlN846-ywkh",
        "outputId": "12afff73-bbb6-4978-e37b-a41d53379abe"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "XqZIHewBy3rh"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}