Model_3_on_Food_101_data_ipynb.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "authorship_tag": "ABX9TyNxSM/l3aP3fAKjk77jn7tq",
      "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_3_on_Food_101_data_ipynb.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": "9RFO77eK1Y3H"
      },
      "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": "HeS7D_7x2Dr7"
      },
      "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": "PTgh6EuW46fa",
        "outputId": "25e71b71-dd65-4db1-8b9c-526537806381"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2024-08-20 08:11:22--  https://storage.googleapis.com/ztm_tf_course/food_vision/101_food_classes_10_percent.zip\n",
            "Resolving storage.googleapis.com (storage.googleapis.com)... 142.251.2.207, 142.250.141.207, 74.125.137.207, ...\n",
            "Connecting to storage.googleapis.com (storage.googleapis.com)|142.251.2.207|: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   107MB/s    in 19s     \n",
            "\n",
            "2024-08-20 08:11:41 (82.9 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": "BT11DWp_4-FC",
        "outputId": "5b12e82d-a78d-4a37-d9cf-89a65a2a6abe"
      },
      "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": "Z4p2CP4B5AsS"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "base_model = tf.keras.applications.EfficientNetB0(include_top=False)\n",
        "base_model.trainable = True"
      ],
      "metadata": {
        "id": "lP0sr_vs5DCL",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "c8b3c9ac-7dea-43e3-8175-f02c65d1d1bf"
      },
      "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": [
        "for layer in base_model.layers[:-10]:\n",
        "    layer.trainable = False"
      ],
      "metadata": {
        "id": "UNyimsRt5N8y"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "inputs = layers.Input(shape=(224, 224, 3), name=\"input_layer\")\n",
        "x = data_augmentation(inputs)\n",
        "x = base_model(x)\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": "Cz5OqtpN5QWZ"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.compile(\n",
        "    loss=\"sparse_categorical_crossentropy\",\n",
        "    optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),  # Lower learning rate for fine-tuning\n",
        "    metrics=[\"accuracy\"]\n",
        ")"
      ],
      "metadata": {
        "id": "niKWKvBt5SLJ"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=\"logs/fine_tuning\")\n",
        "checkpoint_callback = tf.keras.callbacks.ModelCheckpoint(\"fine_tuned_model.keras\", save_best_only=True)"
      ],
      "metadata": {
        "id": "oFzwKixi5V-x"
      },
      "execution_count": 10,
      "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": "7v8E9iRq5YO5",
        "outputId": "760db07f-9830-44fb-e707-16e33f58d791"
      },
      "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[1m72s\u001b[0m 222ms/step - accuracy: 0.0422 - loss: 4.5065 - val_accuracy: 0.2268 - val_loss: 3.7513\n",
            "Epoch 2/5\n",
            "\u001b[1m237/237\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 197ms/step - accuracy: 0.2312 - loss: 3.6645 - val_accuracy: 0.3522 - val_loss: 2.8611\n",
            "Epoch 3/5\n",
            "\u001b[1m237/237\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 193ms/step - accuracy: 0.3386 - loss: 3.0639 - val_accuracy: 0.4294 - val_loss: 2.3734\n",
            "Epoch 4/5\n",
            "\u001b[1m237/237\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m80s\u001b[0m 186ms/step - accuracy: 0.3988 - loss: 2.7098 - val_accuracy: 0.4754 - val_loss: 2.1295\n",
            "Epoch 5/5\n",
            "\u001b[1m237/237\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 127ms/step - accuracy: 0.4345 - loss: 2.4721 - val_accuracy: 0.4412 - val_loss: 2.1377\n"
          ]
        },
        {
          "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"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "results_feature_extraction_model = model.evaluate(test_data)\n",
        "results_feature_extraction_model"
      ],
      "metadata": {
        "id": "a2dMas2i5ahC",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "574255c2-970e-488c-d2c4-113203580c36"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m790/790\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m59s\u001b[0m 74ms/step - accuracy: 0.4874 - loss: 2.0333\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[2.0241615772247314, 0.4883960485458374]"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!wget https://raw.githubusercontent.com/mrdbourke/tensorflow-deep-learning/main/extras/helper_functions.py"
      ],
      "metadata": {
        "id": "M5WCakAN3_Wa",
        "outputId": "5c7df91c-dc22-4d0e-9575-a71c0eea6df1",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2024-08-20 08:22:19--  https://raw.githubusercontent.com/mrdbourke/tensorflow-deep-learning/main/extras/helper_functions.py\n",
            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.109.133, 185.199.110.133, 185.199.108.133, ...\n",
            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.109.133|: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 0.001s  \n",
            "\n",
            "2024-08-20 08:22:19 (18.1 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": "wNODrIIu4DLS"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plot_loss_curves(history)"
      ],
      "metadata": {
        "id": "yRKdcKPz4FPh",
        "outputId": "4b1f096d-6e7b-4fb4-8738-c8b3b8cf6197",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 927
        }
      },
      "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": "JMdx3Spu4IVE"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}