{"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":"2024-07-24T15:11:46.911569Z","iopub.execute_input":"2024-07-24T15:11:46.912878Z","iopub.status.idle":"2024-07-24T15:11:48.088515Z","shell.execute_reply.started":"2024-07-24T15:11:46.912840Z","shell.execute_reply":"2024-07-24T15:11:48.087230Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport zipfile\nimport shutil\n\n# データセットのパスを設定\ntrain_zip_path = '/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip'\ntest_zip_path = '/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip'\ntrain_dir = '/kaggle/working/train'\ntest_dir = '/kaggle/working/test'\n\n# ディレクトリを作成\nos.makedirs(train_dir, exist_ok=True)\nos.makedirs(test_dir, exist_ok=True)\n\n# ZIPファイルを解凍\nwith zipfile.ZipFile(train_zip_path, 'r') as zip_ref:\n    zip_ref.extractall(train_dir)\n    \nwith zipfile.ZipFile(test_zip_path, 'r') as zip_ref:\n    zip_ref.extractall(test_dir)\n\n# サブディレクトリを作成\ntrain_dog_dir = os.path.join(train_dir, 'train', 'dog')\ntrain_cat_dir = os.path.join(train_dir, 'train', 'cat')\nos.makedirs(train_dog_dir, exist_ok=True)\nos.makedirs(train_cat_dir, exist_ok=True)\n\n# 画像をサブディレクトリに移動\nfor filename in os.listdir(os.path.join(train_dir, 'train')):\n    if 'dog' in filename:\n        shutil.move(os.path.join(train_dir, 'train', filename), train_dog_dir)\n    elif 'cat' in filename:\n        shutil.move(os.path.join(train_dir, 'train', filename), train_cat_dir)\n\n# 新しいディレクトリ構造の確認\nprint(\"Dog images:\", len(os.listdir(train_dog_dir)))\nprint(\"Cat images:\", len(os.listdir(train_cat_dir)))","metadata":{"execution":{"iopub.status.busy":"2024-07-24T15:11:48.091522Z","iopub.execute_input":"2024-07-24T15:11:48.091954Z","iopub.status.idle":"2024-07-24T15:12:06.643132Z","shell.execute_reply.started":"2024-07-24T15:11:48.091927Z","shell.execute_reply":"2024-07-24T15:12:06.642029Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator\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  # 訓練データの20%を検証データとして使用\n)\n\ntrain_generator = train_datagen.flow_from_directory(\n    os.path.join(train_dir, 'train'),\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    os.path.join(train_dir, 'train'),\n    target_size=(150, 150),\n    batch_size=32,\n    class_mode='binary',\n    subset='validation'\n)","metadata":{"execution":{"iopub.status.busy":"2024-07-24T20:58:58.688358Z","iopub.execute_input":"2024-07-24T20:58:58.689479Z","iopub.status.idle":"2024-07-24T20:59:04.720483Z","shell.execute_reply.started":"2024-07-24T20:58:58.689441Z","shell.execute_reply":"2024-07-24T20:59:04.719256Z"},"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'])","metadata":{"execution":{"iopub.status.busy":"2024-07-24T20:59:09.796720Z","iopub.execute_input":"2024-07-24T20:59:09.797513Z","iopub.status.idle":"2024-07-24T20:59:10.094235Z","shell.execute_reply.started":"2024-07-24T20:59:09.797477Z","shell.execute_reply":"2024-07-24T20:59:10.092851Z"},"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=10,\n    callbacks=[early_stopping]\n)\n","metadata":{"execution":{"iopub.status.busy":"2024-07-24T20:59:16.083993Z","iopub.execute_input":"2024-07-24T20:59:16.084426Z","iopub.status.idle":"2024-07-24T22:01:15.013960Z","shell.execute_reply.started":"2024-07-24T20:59:16.084394Z","shell.execute_reply":"2024-07-24T22:01:15.010669Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# モデルの評価\nloss, accuracy = model.evaluate(validation_generator)\nprint(f'Validation Loss: {loss}')\nprint(f'Validation Accuracy: {accuracy}')\n\n\n# モデルの保存\nmodel.save('cats_vs_dogs_model.h5')","metadata":{"execution":{"iopub.status.busy":"2024-07-24T22:01:56.030239Z","iopub.execute_input":"2024-07-24T22:01:56.030710Z","iopub.status.idle":"2024-07-24T22:02:56.248381Z","shell.execute_reply.started":"2024-07-24T22:01:56.030678Z","shell.execute_reply":"2024-07-24T22:02:56.246676Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# テストデータジェネレータの設定\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\ntest_generator = test_datagen.flow_from_directory(\n    os.path.join(test_dir),\n    target_size=(150, 150),\n    batch_size=32,\n    class_mode=None,\n    shuffle=False\n)\n\n# 予測の実行\npredictions = model.predict(test_generator)\npredicted_classes = (predictions > 0.5).astype(int).flatten()\n\n# 提出用データフレームの作成\nimport pandas as pd\n\nfilenames = test_generator.filenames\nresults = pd.DataFrame({'id': [int(f.split('/')[1].split('.')[0]) for f in filenames], 'label': predicted_classes})\nresults = results.sort_values(by='id')\n\n# 提出ファイルの保存\nresults.to_csv('submission.csv', index=False)\n","metadata":{"execution":{"iopub.status.busy":"2024-07-24T22:03:04.926235Z","iopub.execute_input":"2024-07-24T22:03:04.926639Z","iopub.status.idle":"2024-07-24T22:05:17.083591Z","shell.execute_reply.started":"2024-07-24T22:03:04.926610Z","shell.execute_reply":"2024-07-24T22:05:17.081846Z"},"trusted":true},"execution_count":null,"outputs":[]}]}