{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":5441,"databundleVersionId":38425,"sourceType":"competition"}],"dockerImageVersionId":30746,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-07-12T07:02:44.687177Z","iopub.execute_input":"2024-07-12T07:02:44.688438Z","iopub.status.idle":"2024-07-12T07:02:44.698497Z","shell.execute_reply.started":"2024-07-12T07:02:44.688397Z","shell.execute_reply":"2024-07-12T07:02:44.697105Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nimport os\nimport zipfile\n","metadata":{"execution":{"iopub.status.busy":"2024-07-12T07:02:47.797959Z","iopub.execute_input":"2024-07-12T07:02:47.799314Z","iopub.status.idle":"2024-07-12T07:02:47.804655Z","shell.execute_reply.started":"2024-07-12T07:02:47.799270Z","shell.execute_reply":"2024-07-12T07:02:47.803340Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport zipfile\n\n# トレーニングデータの解凍\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip', 'r') as zip_ref:\n    zip_ref.extractall('/kaggle/working/train')\n\n# テストデータの解凍\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip', 'r') as zip_ref:\n    zip_ref.extractall('/kaggle/working/test')\n\n# 解凍したディレクトリの内容を確認\nprint(\"Training data:\", os.listdir('/kaggle/working/train'))\nprint(\"Test data:\", os.listdir('/kaggle/working/test'))\n","metadata":{"execution":{"iopub.status.busy":"2024-07-12T07:02:51.379583Z","iopub.execute_input":"2024-07-12T07:02:51.379999Z","iopub.status.idle":"2024-07-12T07:03:04.824260Z","shell.execute_reply.started":"2024-07-12T07:02:51.379966Z","shell.execute_reply":"2024-07-12T07:03:04.822809Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport shutil\n\n# トレーニングデータのディレクトリを再配置\ntrain_subdir = '/kaggle/working/train/train'\nif not os.path.exists(train_subdir):\n    os.makedirs(train_subdir)\nfor filename in os.listdir('/kaggle/working/train'):\n    if filename != 'train' and not os.path.isdir(os.path.join('/kaggle/working/train', filename)):\n        shutil.move(os.path.join('/kaggle/working/train', filename), train_subdir)\n\n# テストデータのディレクトリを再配置\ntest_subdir = '/kaggle/working/test/test'\nif not os.path.exists(test_subdir):\n    os.makedirs(test_subdir)\nfor filename in os.listdir('/kaggle/working/test'):\n    if filename != 'test' and not os.path.isdir(os.path.join('/kaggle/working/test', filename)):\n        shutil.move(os.path.join('/kaggle/working/test', filename), test_subdir)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport shutil\n\n# 'dog'と'cat'ディレクトリを作成\ndog_dir = '/kaggle/working/train/train/dog'\ncat_dir = '/kaggle/working/train/train/cat'\n\nos.makedirs(dog_dir, exist_ok=True)\nos.makedirs(cat_dir, exist_ok=True)\n\n# 画像ファイルをそれぞれのディレクトリに移動\nfor filename in os.listdir('/kaggle/working/train/train'):\n    if 'dog' in filename:\n        shutil.move(os.path.join('/kaggle/working/train/train', filename), dog_dir)\n    elif 'cat' in filename:\n        shutil.move(os.path.join('/kaggle/working/train/train', filename), cat_dir)\n\n# 新しいディレクトリ構造の確認\nprint(\"Dog images:\", os.listdir(dog_dir)[:5])  # 一部のファイルのみ表示\nprint(\"Cat images:\", os.listdir(cat_dir)[:5])  # 一部のファイルのみ表示\n","metadata":{"execution":{"iopub.status.busy":"2024-07-12T07:07:40.945046Z","iopub.execute_input":"2024-07-12T07:07:40.946229Z","iopub.status.idle":"2024-07-12T07:07:42.468513Z","shell.execute_reply.started":"2024-07-12T07:07:40.946164Z","shell.execute_reply":"2024-07-12T07:07:42.467205Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# データセットのパスを設定\ntrain_dir = '/kaggle/working/train/train'\ntest_dir = '/kaggle/working/test/test'\n\n# 画像データジェネレータの設定\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True,\n    validation_split=0.2\n)\n\ntrain_generator = train_datagen.flow_from_directory(\n    train_dir,\n    target_size=(150, 150),\n    batch_size=32,\n    class_mode='binary',\n    subset='training'\n)\n\nvalidation_generator = train_datagen.flow_from_directory(\n    train_dir,\n    target_size=(150, 150),\n    batch_size=32,\n    class_mode='binary',\n    subset='validation'\n)\n","metadata":{"execution":{"iopub.status.busy":"2024-07-12T07:08:23.713957Z","iopub.execute_input":"2024-07-12T07:08:23.715294Z","iopub.status.idle":"2024-07-12T07:08:24.618460Z","shell.execute_reply.started":"2024-07-12T07:08:23.715236Z","shell.execute_reply":"2024-07-12T07:08:24.617364Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\n\ndog_images = os.listdir('/kaggle/working/train/train/dog')\ncat_images = os.listdir('/kaggle/working/train/train/cat')\n\nprint(f\"Number of dog images: {len(dog_images)}\")\nprint(f\"Number of cat images: {len(cat_images)}\")\n","metadata":{"execution":{"iopub.status.busy":"2024-07-12T07:09:37.370368Z","iopub.execute_input":"2024-07-12T07:09:37.370813Z","iopub.status.idle":"2024-07-12T07:09:37.394894Z","shell.execute_reply.started":"2024-07-12T07:09:37.370783Z","shell.execute_reply":"2024-07-12T07:09:37.393722Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport shutil\n\n# 'dog'と'cat'ディレクトリを再作成\ndog_dir = '/kaggle/working/train/train/dog'\ncat_dir = '/kaggle/working/train/train/cat'\n\nos.makedirs(dog_dir, exist_ok=True)\nos.makedirs(cat_dir, exist_ok=True)\n\n# 画像ファイルをそれぞれのディレクトリに移動\nfor filename in os.listdir('/kaggle/working/train/train'):\n    if 'dog' in filename:\n        shutil.move(os.path.join('/kaggle/working/train/train', filename), dog_dir)\n    elif 'cat' in filename:\n        shutil.move(os.path.join('/kaggle/working/train/train', filename), cat_dir)\n\n# 新しいディレクトリ構造の確認\nprint(\"Dog images:\", len(os.listdir(dog_dir)))\nprint(\"Cat images:\", len(os.listdir(cat_dir)))\n","metadata":{"execution":{"iopub.status.busy":"2024-07-12T07:10:06.724129Z","iopub.execute_input":"2024-07-12T07:10:06.724547Z","iopub.status.idle":"2024-07-12T07:10:06.753408Z","shell.execute_reply.started":"2024-07-12T07:10:06.724513Z","shell.execute_reply":"2024-07-12T07:10:06.752169Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport shutil\n\n# 'dog'と'cat'ディレクトリを再作成\ndog_dir = '/kaggle/working/train/train/dog'\ncat_dir = '/kaggle/working/train/train/cat'\n\nos.makedirs(dog_dir, exist_ok=True)\nos.makedirs(cat_dir, exist_ok=True)\n\n# 画像ファイルをそれぞれのディレクトリに移動\nfor filename in os.listdir('/kaggle/working/train/train'):\n    if 'dog' in filename:\n        shutil.move(os.path.join('/kaggle/working/train/train', filename), dog_dir)\n    elif 'cat' in filename:\n        shutil.move(os.path.join('/kaggle/working/train/train', filename), cat_dir)\n\n# 新しいディレクトリ構造の確認\nprint(\"Dog images:\", len(os.listdir(dog_dir)))\nprint(\"Cat images:\", len(os.listdir(cat_dir)))\n","metadata":{"execution":{"iopub.status.busy":"2024-07-12T07:10:19.512362Z","iopub.execute_input":"2024-07-12T07:10:19.512792Z","iopub.status.idle":"2024-07-12T07:10:19.540618Z","shell.execute_reply.started":"2024-07-12T07:10:19.512757Z","shell.execute_reply":"2024-07-12T07:10:19.539172Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# データセットのパスを設定\ntrain_dir = '/kaggle/working/train/train'\ntest_dir = '/kaggle/working/test/test'\n\n# 画像データジェネレータの設定\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True,\n    validation_split=0.2\n)\n\ntrain_generator = train_datagen.flow_from_directory(\n    train_dir,\n    target_size=(150, 150),\n    batch_size=32,\n    class_mode='binary',\n    subset='training'\n)\n\nvalidation_generator = train_datagen.flow_from_directory(\n    train_dir,\n    target_size=(150, 150),\n    batch_size=32,\n    class_mode='binary',\n    subset='validation'\n)\n","metadata":{"execution":{"iopub.status.busy":"2024-07-12T07:10:32.666619Z","iopub.execute_input":"2024-07-12T07:10:32.667033Z","iopub.status.idle":"2024-07-12T07:10:33.588894Z","shell.execute_reply.started":"2024-07-12T07:10:32.666999Z","shell.execute_reply":"2024-07-12T07:10:33.587646Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.callbacks import EarlyStopping\n\n# モデルの構築\nmodel = Sequential([\n    Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)),\n    MaxPooling2D(pool_size=(2, 2)),\n    Conv2D(64, (3, 3), activation='relu'),\n    MaxPooling2D(pool_size=(2, 2)),\n    Conv2D(128, (3, 3), activation='relu'),\n    MaxPooling2D(pool_size=(2, 2)),\n    Flatten(),\n    Dense(512, activation='relu'),\n    Dropout(0.5),\n    Dense(1, activation='sigmoid')\n])\n\n# モデルのコンパイル\nmodel.compile(optimizer=Adam(learning_rate=0.001), loss='binary_crossentropy', metrics=['accuracy'])\n","metadata":{"execution":{"iopub.status.busy":"2024-07-12T07:11:31.375014Z","iopub.execute_input":"2024-07-12T07:11:31.375514Z","iopub.status.idle":"2024-07-12T07:11:31.733973Z","shell.execute_reply.started":"2024-07-12T07:11:31.375480Z","shell.execute_reply":"2024-07-12T07:11:31.732928Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 早期終了の設定\nearly_stopping = EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True)\n\n# モデルの訓練\nhistory = model.fit(\n    train_generator,\n    steps_per_epoch=train_generator.samples // train_generator.batch_size,\n    validation_data=validation_generator,\n    validation_steps=validation_generator.samples // validation_generator.batch_size,\n    epochs=50,\n    callbacks=[early_stopping]\n)\n","metadata":{"execution":{"iopub.status.busy":"2024-07-12T07:11:45.411809Z","iopub.execute_input":"2024-07-12T07:11:45.412252Z"},"trusted":true},"execution_count":null,"outputs":[]}]}