tutorial_screw_training_ce.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "268ce6c2",
   "metadata": {},
   "source": [
    "### [Optional] Reset the data folder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "24b6b263",
   "metadata": {},
   "outputs": [],
   "source": [
    "!rm -rf ./data/original/ ./data/arrange/ ~/.kaggle/"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7def5f95",
   "metadata": {},
   "source": [
    "## Part 1: Fill in the Variable \n",
    "Please modify the variable to get the correct information."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d5ab5756",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Kaggle connection\n",
    "kaggle_api_token = {\"username\":<username>,\"key\":<access-key>}\n",
    "\n",
    "# Label Data file\n",
    "label_data_file_path = \"project-6-at-2022-09-19-04-17-b9f72b54.json\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "880271ab",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Model learning rate\n",
    "base_learning_rate = 0.01"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e2137e08",
   "metadata": {},
   "outputs": [],
   "source": [
    "# MLFlow experiment name\n",
    "mlflow_experiment_name = \"tutorial_screw_train\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c4c62c4a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# MLFlow tracking uri\n",
    "mlflow_tracking_uri = \"<mlflow_tracking_uri>\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "898d6e63",
   "metadata": {},
   "source": [
    "## Part 2: Install python package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "dbc8dd2b",
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install -q -r ./jupyter-image/requirements.txt"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "42c322c3",
   "metadata": {},
   "source": [
    "## Part 3: Data Processing"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4822b8fa",
   "metadata": {},
   "source": [
    "### Step 1: Prepare the Data\n",
    "Download and extract the zip file, then follow the tutorial to use Label Studio to label the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "1af222c1",
   "metadata": {},
   "outputs": [],
   "source": [
    "!mkdir ~/.kaggle/\n",
    "!touch ~/.kaggle/kaggle.json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "de9cd0f1",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import json\n",
    "\n",
    "with open('{}/.kaggle/kaggle.json'.format(os.path.expanduser('~')), 'w') as file:\n",
    "    json.dump(kaggle_api_token, file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "1cb5a9a5",
   "metadata": {},
   "outputs": [],
   "source": [
    "!chmod 600 ~/.kaggle/kaggle.json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "381b942c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "mkdir: cannot create directory ‘./data/label/’: File exists\n"
     ]
    }
   ],
   "source": [
    "# Kaggle dataset: https://www.kaggle.com/datasets/ruruamour/screw-dataset\n",
    "\n",
    "# Image data - original\n",
    "original_data_folder_path = \"./data/original/\"\n",
    "!mkdir $original_data_folder_path\n",
    "!kaggle datasets download -d ruruamour/screw-dataset -p ./data/ -q\n",
    "!unzip -q ./data/screw-dataset.zip -d $original_data_folder_path\n",
    "!rm -rf ./data/screw-dataset.zip\n",
    "\n",
    "# Label data folder\n",
    "label_data_folder_path = \"./data/label/\"\n",
    "!mkdir $label_data_folder_path"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "89a29d63",
   "metadata": {},
   "source": [
    "### Step 2: Data ELT pipeline\n",
    "\n",
    "We will do the data ELT pipeline in the following code."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4361a812",
   "metadata": {},
   "source": [
    "#### Import the python package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "645c0fb5",
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import shutil\n",
    "import os\n",
    "from pathlib import Path"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d0e3d660",
   "metadata": {},
   "source": [
    "#### Data Extraction: Read the label studio export json-format file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "7a4e20a2",
   "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>image</th>\n",
       "      <th>id</th>\n",
       "      <th>choice</th>\n",
       "      <th>annotator</th>\n",
       "      <th>annotation_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ok001.png</td>\n",
       "      <td>40</td>\n",
       "      <td>good</td>\n",
       "      <td>demo@infuseai.io</td>\n",
       "      <td>44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ok002.png</td>\n",
       "      <td>39</td>\n",
       "      <td>good</td>\n",
       "      <td>demo@infuseai.io</td>\n",
       "      <td>43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ok003.png</td>\n",
       "      <td>38</td>\n",
       "      <td>good</td>\n",
       "      <td>demo@infuseai.io</td>\n",
       "      <td>42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ok004.png</td>\n",
       "      <td>37</td>\n",
       "      <td>good</td>\n",
       "      <td>demo@infuseai.io</td>\n",
       "      <td>41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ok005.png</td>\n",
       "      <td>36</td>\n",
       "      <td>good</td>\n",
       "      <td>demo@infuseai.io</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       image  id choice         annotator  annotation_id\n",
       "0  ok001.png  40   good  demo@infuseai.io             44\n",
       "1  ok002.png  39   good  demo@infuseai.io             43\n",
       "2  ok003.png  38   good  demo@infuseai.io             42\n",
       "3  ok004.png  37   good  demo@infuseai.io             41\n",
       "4  ok005.png  36   good  demo@infuseai.io             40"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df = pd.read_json(os.path.join(label_data_folder_path, label_data_file_path))\n",
    "df['image'] = df['image'].str.split(pat=\"/\", expand=True)[8]\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "336229cd",
   "metadata": {},
   "source": [
    "#### Data Load-To: Create a training and validation data folder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "208c7b24",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'train': {'folder_path': './data/arrange/train',\n",
       "  'good': {'folder_path': './data/arrange/train/good'},\n",
       "  'bad': {'folder_path': './data/arrange/train/bad'}},\n",
       " 'valid': {'folder_path': './data/arrange/valid',\n",
       "  'good': {'folder_path': './data/arrange/valid/good'},\n",
       "  'bad': {'folder_path': './data/arrange/valid/bad'}}}"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arrange_data_folder_path = './data/arrange/'\n",
    "dataset_type_list = ['train', 'valid']\n",
    "label_list = ['good', 'bad']\n",
    "dataset_dict = {}\n",
    "\n",
    "for dataset_type in dataset_type_list:\n",
    "    dataset_dict[dataset_type] = {}\n",
    "    dataset_dict[dataset_type]['folder_path'] = os.path.join(arrange_data_folder_path, dataset_type)\n",
    "    for label in label_list:\n",
    "        arrange_subfolder_path = os.path.join(arrange_data_folder_path, dataset_type, label)\n",
    "        dataset_dict[dataset_type][label] = {}\n",
    "        dataset_dict[dataset_type][label]['folder_path'] = arrange_subfolder_path\n",
    "        os.makedirs(arrange_subfolder_path, exist_ok=True)\n",
    "    \n",
    "dataset_dict"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f9156c62",
   "metadata": {},
   "source": [
    "#### Data Transformation: Put the original image data into arrangement folder."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "a5b71533",
   "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>image</th>\n",
       "      <th>id</th>\n",
       "      <th>choice</th>\n",
       "      <th>annotator</th>\n",
       "      <th>annotation_id</th>\n",
       "      <th>arrange_path</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ok001.png</td>\n",
       "      <td>40</td>\n",
       "      <td>good</td>\n",
       "      <td>demo@infuseai.io</td>\n",
       "      <td>44</td>\n",
       "      <td>./data/arrange/valid/good/ok001.png</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ok002.png</td>\n",
       "      <td>39</td>\n",
       "      <td>good</td>\n",
       "      <td>demo@infuseai.io</td>\n",
       "      <td>43</td>\n",
       "      <td>./data/arrange/valid/good/ok002.png</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ok003.png</td>\n",
       "      <td>38</td>\n",
       "      <td>good</td>\n",
       "      <td>demo@infuseai.io</td>\n",
       "      <td>42</td>\n",
       "      <td>./data/arrange/valid/good/ok003.png</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ok004.png</td>\n",
       "      <td>37</td>\n",
       "      <td>good</td>\n",
       "      <td>demo@infuseai.io</td>\n",
       "      <td>41</td>\n",
       "      <td>./data/arrange/valid/good/ok004.png</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ok005.png</td>\n",
       "      <td>36</td>\n",
       "      <td>good</td>\n",
       "      <td>demo@infuseai.io</td>\n",
       "      <td>40</td>\n",
       "      <td>./data/arrange/train/good/ok005.png</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       image  id choice         annotator  annotation_id  \\\n",
       "0  ok001.png  40   good  demo@infuseai.io             44   \n",
       "1  ok002.png  39   good  demo@infuseai.io             43   \n",
       "2  ok003.png  38   good  demo@infuseai.io             42   \n",
       "3  ok004.png  37   good  demo@infuseai.io             41   \n",
       "4  ok005.png  36   good  demo@infuseai.io             40   \n",
       "\n",
       "                          arrange_path  \n",
       "0  ./data/arrange/valid/good/ok001.png  \n",
       "1  ./data/arrange/valid/good/ok002.png  \n",
       "2  ./data/arrange/valid/good/ok003.png  \n",
       "3  ./data/arrange/valid/good/ok004.png  \n",
       "4  ./data/arrange/train/good/ok005.png  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "val_count = 4\n",
    "val_good_count = 0\n",
    "val_bad_count = 0\n",
    "\n",
    "arrange_folder_path_list = []\n",
    "for original_file_name, label_result in zip(df['image'], df['choice']):\n",
    "    original_file_path = os.path.join(original_data_folder_path, 'train', original_file_name)\n",
    "    if label_result == 'good':\n",
    "        if val_good_count < val_count:\n",
    "            arrange_file_path = os.path.join(dataset_dict['valid']['good']['folder_path'], original_file_name)\n",
    "            val_good_count = val_good_count + 1\n",
    "        else:\n",
    "            arrange_file_path = os.path.join(dataset_dict['train']['good']['folder_path'], original_file_name)\n",
    "    else:\n",
    "        if val_bad_count < val_count:\n",
    "            arrange_file_path = os.path.join(dataset_dict['valid']['bad']['folder_path'], original_file_name)\n",
    "            val_bad_count = val_bad_count + 1\n",
    "        else:\n",
    "            arrange_file_path = os.path.join(dataset_dict['train']['bad']['folder_path'], original_file_name)\n",
    "    arrange_folder_path_list.append(arrange_file_path)\n",
    "    shutil.copyfile(original_file_path, arrange_file_path)\n",
    "\n",
    "df['arrange_path'] = arrange_folder_path_list\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a5f9f675",
   "metadata": {},
   "source": [
    "## Part 3: Model Training Pipeline\n",
    "\n",
    "After labeled all the images, you can run the following cells to start training and log results to MLflow."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bf4c81c7",
   "metadata": {},
   "source": [
    "### Step 1: Import python package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "edcd701e",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-05-09 04:09:45.594977: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: \n",
      "2023-05-09 04:09:45.595033: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import numpy as np\n",
    "import tensorflow as tf\n",
    "import tensorflow_hub as hub\n",
    "import matplotlib.pyplot as plt\n",
    "from tensorflow.keras.preprocessing import image_dataset_from_directory"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e73070c5",
   "metadata": {},
   "source": [
    "### Step 2: mlflow initial"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "655fba4a",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023/05/09 04:09:48 WARNING mlflow.utils.autologging_utils: You are using an unsupported version of tensorflow. If you encounter errors during autologging, try upgrading / downgrading tensorflow to a supported version, or try upgrading MLflow.\n"
     ]
    }
   ],
   "source": [
    "import mlflow\n",
    "mlflow.set_tracking_uri(mlflow_tracking_uri)\n",
    "mlflow.set_experiment(mlflow_experiment_name)\n",
    "mlflow.tensorflow.autolog()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9d934920",
   "metadata": {},
   "source": [
    "### Step 3: Setting dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "73620f04",
   "metadata": {},
   "outputs": [],
   "source": [
    "BATCH_SIZE = 8\n",
    "IMG_SIZE = (1024, 1024)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "504a9c6a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 32 files belonging to 2 classes.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-05-09 04:09:48.592791: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: \n",
      "2023-05-09 04:09:48.592832: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)\n",
      "2023-05-09 04:09:48.592851: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (jupyter-phadmin): /proc/driver/nvidia/version does not exist\n",
      "2023-05-09 04:09:48.593132: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
     ]
    }
   ],
   "source": [
    "train_dataset = image_dataset_from_directory(dataset_dict['train']['folder_path'],\n",
    "                                             shuffle=True,\n",
    "                                             batch_size=BATCH_SIZE,\n",
    "                                             image_size=IMG_SIZE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "aa4a2895",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 8 files belonging to 2 classes.\n"
     ]
    }
   ],
   "source": [
    "validation_dataset = image_dataset_from_directory(dataset_dict['valid']['folder_path'],\n",
    "                                                  shuffle=True,\n",
    "                                                  batch_size=BATCH_SIZE,\n",
    "                                                  image_size=IMG_SIZE)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bdbabfb9",
   "metadata": {},
   "source": [
    "#### Show example\n",
    "Show some cases of training examples."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "d1a4d9ad",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 6 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "class_names = train_dataset.class_names\n",
    "\n",
    "show_img = 1\n",
    "\n",
    "if show_img:\n",
    "    plt.figure(figsize=(10, 10))\n",
    "    for images, labels in train_dataset.take(1):\n",
    "        for i in range(6):\n",
    "            ax = plt.subplot(3, 3, i + 1)\n",
    "            plt.imshow(images[i].numpy().astype(\"uint8\"))\n",
    "            plt.title(class_names[labels[i]])\n",
    "            plt.axis(\"off\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "87ff30cb",
   "metadata": {},
   "source": [
    "### Step 4: Build the Model\n",
    "We use mobilenet as our model."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "73902437",
   "metadata": {},
   "source": [
    "#### Build the data augmentation layer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "b51342a9",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_augmentation = tf.keras.Sequential([\n",
    "    tf.keras.layers.experimental.preprocessing.RandomFlip(),\n",
    "])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "73731f36",
   "metadata": {},
   "source": [
    "#### Build the Input preprocessing application layer\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "e802040c",
   "metadata": {},
   "outputs": [],
   "source": [
    "preprocess_input = tf.keras.applications.mobilenet_v2.preprocess_input"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ee86caa8",
   "metadata": {},
   "source": [
    "#### Build the mobilenet v3 base model\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "53648afd",
   "metadata": {},
   "outputs": [],
   "source": [
    "model_url = \"https://tfhub.dev/google/imagenet/mobilenet_v3_large_100_224/feature_vector/5\"\n",
    "base_model = tf.keras.Sequential([\n",
    "    tf.keras.layers.experimental.preprocessing.Resizing(224, 224),\n",
    "    hub.KerasLayer(model_url, trainable=False)\n",
    "])\n",
    "base_model.build([None, 224, 224, 3])\n",
    "\n",
    "# Change base model trainable is False(We only fine-tune the model in this example.)\n",
    "base_model.trainable = False"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9cf30a2b",
   "metadata": {},
   "source": [
    "#### Build the prediction layer\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "5754862f",
   "metadata": {},
   "outputs": [],
   "source": [
    "prediction_layer = tf.keras.layers.Dense(1, kernel_regularizer=tf.keras.regularizers.l2(l2=0.1))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "87655e79",
   "metadata": {},
   "source": [
    "#### Combine all the model layer into one model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "a693debb",
   "metadata": {},
   "outputs": [],
   "source": [
    "inputs = tf.keras.Input(shape=(1024, 1024, 3))\n",
    "x = data_augmentation(inputs)\n",
    "x = preprocess_input(x)\n",
    "x = base_model(x, training=False)\n",
    "outputs = prediction_layer(x)\n",
    "model = tf.keras.Model(inputs, outputs)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2cc74ce8",
   "metadata": {
    "tags": [
     "parameters"
    ]
   },
   "source": [
    "#### Compile the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "f8ee13da",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.7/site-packages/keras/optimizer_v2/gradient_descent.py:102: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.\n",
      "  super(SGD, self).__init__(name, **kwargs)\n"
     ]
    }
   ],
   "source": [
    "model.compile(optimizer=tf.keras.optimizers.SGD(lr=base_learning_rate, momentum=0.9),\n",
    "              loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),\n",
    "              metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0944ca3c",
   "metadata": {},
   "source": [
    "#### Get the model summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "48ee2d84",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"model\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " input_1 (InputLayer)        [(None, 1024, 1024, 3)]   0         \n",
      "                                                                 \n",
      " sequential (Sequential)     (None, 1024, 1024, 3)     0         \n",
      "                                                                 \n",
      " tf.math.truediv (TFOpLambda  (None, 1024, 1024, 3)    0         \n",
      " )                                                               \n",
      "                                                                 \n",
      " tf.math.subtract (TFOpLambd  (None, 1024, 1024, 3)    0         \n",
      " a)                                                              \n",
      "                                                                 \n",
      " sequential_1 (Sequential)   (None, 1280)              4226432   \n",
      "                                                                 \n",
      " dense (Dense)               (None, 1)                 1281      \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 4,227,713\n",
      "Trainable params: 1,281\n",
      "Non-trainable params: 4,226,432\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "180bfad5",
   "metadata": {},
   "source": [
    "### Step 5: Model Training"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c71e5408",
   "metadata": {},
   "source": [
    "#### Check the initial dataset metrics value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "456d6459",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 2s 2s/step - loss: 1.0695 - accuracy: 0.3750\n"
     ]
    }
   ],
   "source": [
    "loss0, accuracy0 = model.evaluate(validation_dataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "59496033",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "initial loss: 1.07\n",
      "initial accuracy: 0.38\n"
     ]
    }
   ],
   "source": [
    "print(\"initial loss: {:.2f}\".format(loss0))\n",
    "print(\"initial accuracy: {:.2f}\".format(accuracy0))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "695b140e",
   "metadata": {},
   "source": [
    "#### Setting the callback"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "a5dec248",
   "metadata": {},
   "outputs": [],
   "source": [
    "def scheduler(epoch, lr):\n",
    "    if epoch >= 10 and epoch % 10 == 0:\n",
    "        return lr / 5\n",
    "    return lr\n",
    "\n",
    "learning_rate_scheduler = tf.keras.callbacks.LearningRateScheduler(scheduler)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "b62a16a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "callback_list = [learning_rate_scheduler]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd7c4fd8",
   "metadata": {},
   "source": [
    "#### Train the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "184e0fa6",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023/05/09 04:09:56 INFO mlflow.utils.autologging_utils: Created MLflow autologging run with ID '23ddd6e351ff4007ab1da6464b32cd6c', which will track hyperparameters, performance metrics, model artifacts, and lineage information for the current tensorflow workflow\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/25\n",
      "4/4 [==============================] - 11s 1s/step - loss: 0.6720 - accuracy: 0.8125 - val_loss: 1.0889 - val_accuracy: 0.3750 - lr: 0.0100\n",
      "Epoch 2/25\n",
      "4/4 [==============================] - 5s 1s/step - loss: 0.6069 - accuracy: 0.8125 - val_loss: 0.9019 - val_accuracy: 0.5000 - lr: 0.0100\n",
      "Epoch 3/25\n",
      "4/4 [==============================] - 5s 1s/step - loss: 0.6029 - accuracy: 0.8438 - val_loss: 1.2302 - val_accuracy: 0.5000 - lr: 0.0100\n",
      "Epoch 4/25\n",
      "4/4 [==============================] - 5s 1s/step - loss: 0.5434 - accuracy: 0.7812 - val_loss: 1.1417 - val_accuracy: 0.6250 - lr: 0.0100\n",
      "Epoch 5/25\n",
      "4/4 [==============================] - 5s 1s/step - loss: 0.4039 - accuracy: 0.9375 - val_loss: 1.1664 - val_accuracy: 0.5000 - lr: 0.0100\n",
      "Epoch 6/25\n",
      "4/4 [==============================] - 4s 987ms/step - loss: 0.4777 - accuracy: 0.8750 - val_loss: 1.1736 - val_accuracy: 0.6250 - lr: 0.0100\n",
      "Epoch 7/25\n",
      "4/4 [==============================] - 4s 960ms/step - loss: 0.3221 - accuracy: 0.9375 - val_loss: 0.9891 - val_accuracy: 0.6250 - lr: 0.0100\n",
      "Epoch 8/25\n",
      "4/4 [==============================] - 4s 1s/step - loss: 0.2649 - accuracy: 1.0000 - val_loss: 0.8578 - val_accuracy: 0.6250 - lr: 0.0100\n",
      "Epoch 9/25\n",
      "4/4 [==============================] - 5s 1s/step - loss: 0.3047 - accuracy: 0.9688 - val_loss: 0.8711 - val_accuracy: 0.5000 - lr: 0.0100\n",
      "Epoch 10/25\n",
      "4/4 [==============================] - 5s 1s/step - loss: 0.2577 - accuracy: 0.9688 - val_loss: 0.7637 - val_accuracy: 0.7500 - lr: 0.0100\n",
      "Epoch 11/25\n",
      "4/4 [==============================] - 4s 992ms/step - loss: 0.2498 - accuracy: 1.0000 - val_loss: 0.7468 - val_accuracy: 0.7500 - lr: 0.0020\n",
      "Epoch 12/25\n",
      "4/4 [==============================] - 4s 985ms/step - loss: 0.2612 - accuracy: 0.9688 - val_loss: 0.7997 - val_accuracy: 0.5000 - lr: 0.0020\n",
      "Epoch 13/25\n",
      "4/4 [==============================] - 4s 1s/step - loss: 0.2481 - accuracy: 1.0000 - val_loss: 0.8439 - val_accuracy: 0.5000 - lr: 0.0020\n",
      "Epoch 14/25\n",
      "4/4 [==============================] - 5s 1s/step - loss: 0.2127 - accuracy: 1.0000 - val_loss: 0.8209 - val_accuracy: 0.5000 - lr: 0.0020\n",
      "Epoch 15/25\n",
      "4/4 [==============================] - 5s 1s/step - loss: 0.2401 - accuracy: 1.0000 - val_loss: 0.8120 - val_accuracy: 0.5000 - lr: 0.0020\n",
      "Epoch 16/25\n",
      "4/4 [==============================] - 4s 993ms/step - loss: 0.2609 - accuracy: 0.9375 - val_loss: 0.8012 - val_accuracy: 0.5000 - lr: 0.0020\n",
      "Epoch 17/25\n",
      "4/4 [==============================] - 5s 1s/step - loss: 0.2222 - accuracy: 1.0000 - val_loss: 0.7645 - val_accuracy: 0.5000 - lr: 0.0020\n",
      "Epoch 18/25\n",
      "4/4 [==============================] - 4s 948ms/step - loss: 0.2288 - accuracy: 1.0000 - val_loss: 0.7339 - val_accuracy: 0.7500 - lr: 0.0020\n",
      "Epoch 19/25\n",
      "4/4 [==============================] - 4s 893ms/step - loss: 0.2459 - accuracy: 1.0000 - val_loss: 0.7321 - val_accuracy: 0.7500 - lr: 0.0020\n",
      "Epoch 20/25\n",
      "4/4 [==============================] - 4s 917ms/step - loss: 0.2197 - accuracy: 1.0000 - val_loss: 0.7634 - val_accuracy: 0.5000 - lr: 0.0020\n",
      "Epoch 21/25\n",
      "4/4 [==============================] - 4s 947ms/step - loss: 0.2380 - accuracy: 0.9688 - val_loss: 0.7837 - val_accuracy: 0.5000 - lr: 4.0000e-04\n",
      "Epoch 22/25\n",
      "4/4 [==============================] - 4s 898ms/step - loss: 0.2353 - accuracy: 0.9688 - val_loss: 0.7966 - val_accuracy: 0.5000 - lr: 4.0000e-04\n",
      "Epoch 23/25\n",
      "4/4 [==============================] - 4s 889ms/step - loss: 0.2291 - accuracy: 0.9688 - val_loss: 0.8008 - val_accuracy: 0.5000 - lr: 4.0000e-04\n",
      "Epoch 24/25\n",
      "4/4 [==============================] - 4s 916ms/step - loss: 0.2252 - accuracy: 1.0000 - val_loss: 0.8002 - val_accuracy: 0.5000 - lr: 4.0000e-04\n",
      "Epoch 25/25\n",
      "4/4 [==============================] - 4s 928ms/step - loss: 0.2245 - accuracy: 0.9688 - val_loss: 0.7929 - val_accuracy: 0.5000 - lr: 4.0000e-04\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-05-09 04:12:09.161655: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Assets written to: /tmp/tmp56sjvsqz/model/data/model/assets\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Assets written to: /tmp/tmp56sjvsqz/model/data/model/assets\n"
     ]
    }
   ],
   "source": [
    "initial_epochs = 25\n",
    "\n",
    "history = model.fit(train_dataset,\n",
    "                    validation_data=validation_dataset,\n",
    "                    epochs=initial_epochs,\n",
    "                    callbacks=callback_list)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fed3fbb9",
   "metadata": {},
   "source": [
    "### Step 6: Model Evaluation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "24f81d12",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 1s 512ms/step - loss: 0.7929 - accuracy: 0.5000\n"
     ]
    }
   ],
   "source": [
    "lossfinal, accuracyfinal = model.evaluate(validation_dataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "c1b48ab8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "final loss: 0.79\n",
      "final accuracy: 0.50\n"
     ]
    }
   ],
   "source": [
    "print(\"final loss: {:.2f}\".format(lossfinal))\n",
    "print(\"final accuracy: {:.2f}\".format(accuracyfinal))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.7.12"
  },
  "vscode": {
   "interpreter": {
    "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}