{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","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":31040,"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","trusted":true,"execution":{"iopub.status.busy":"2025-07-04T07:46:14.827876Z","iopub.execute_input":"2025-07-04T07:46:14.828230Z","iopub.status.idle":"2025-07-04T07:46:17.060208Z","shell.execute_reply.started":"2025-07-04T07:46:14.828196Z","shell.execute_reply":"2025-07-04T07:46:17.059284Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.applications.vgg16 import VGG16\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, Flatten","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-04T08:01:23.621639Z","iopub.execute_input":"2025-07-04T08:01:23.622000Z","iopub.status.idle":"2025-07-04T08:01:23.728566Z","shell.execute_reply.started":"2025-07-04T08:01:23.621975Z","shell.execute_reply":"2025-07-04T08:01:23.727671Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\n\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-04T08:01:28.383953Z","iopub.execute_input":"2025-07-04T08:01:28.384293Z","iopub.status.idle":"2025-07-04T08:01:28.392438Z","shell.execute_reply.started":"2025-07-04T08:01:28.384270Z","shell.execute_reply":"2025-07-04T08:01:28.391375Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\n\ndf = pd.read_csv('/kaggle/input/dogs-vs-cats-redux-kernels-edition/sample_submission.csv')\nprint(df.head())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-04T07:55:55.728692Z","iopub.execute_input":"2025-07-04T07:55:55.729001Z","iopub.status.idle":"2025-07-04T07:55:55.767088Z","shell.execute_reply.started":"2025-07-04T07:55:55.728978Z","shell.execute_reply":"2025-07-04T07:55:55.766046Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import zipfile\n\n\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip', 'r') as zip_ref:\n    \n    file_list = zip_ref.namelist()\n    print(file_list[:10])  ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-04T07:57:37.572607Z","iopub.execute_input":"2025-07-04T07:57:37.573425Z","iopub.status.idle":"2025-07-04T07:57:37.705452Z","shell.execute_reply.started":"2025-07-04T07:57:37.573400Z","shell.execute_reply":"2025-07-04T07:57:37.704309Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from PIL import Image\nimport zipfile\nimport io\nimport matplotlib.pyplot as plt\n\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip', 'r') as zip_ref:\n    file_list = zip_ref.namelist()\n    \n    sample_file = file_list[2]\n    \n    with zip_ref.open(sample_file) as file:\n        img = Image.open(file)\n        plt.imshow(img)\n        plt.title(sample_file)\n        plt.axis('off')\n        plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-04T07:58:34.389284Z","iopub.execute_input":"2025-07-04T07:58:34.390332Z","iopub.status.idle":"2025-07-04T07:58:35.092449Z","shell.execute_reply.started":"2025-07-04T07:58:34.390280Z","shell.execute_reply":"2025-07-04T07:58:35.091443Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import zipfile\nimport os\nimport shutil\n\n# 解凍先ディレクトリ\nbase_dir = '/kaggle/working/dogs-vs-cats'\ntrain_zip = '/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip'\n\n# 解凍\nwith zipfile.ZipFile(train_zip, 'r') as zip_ref:\n    zip_ref.extractall(base_dir)\n\n# 画像を cat / dog フォルダに分ける\ntrain_dir = os.path.join(base_dir, 'train')\ncat_dir = os.path.join(base_dir, 'cats')\ndog_dir = os.path.join(base_dir, 'dogs')\nos.makedirs(cat_dir, exist_ok=True)\nos.makedirs(dog_dir, exist_ok=True)\n\nfor fname in os.listdir(train_dir):\n    if fname.startswith('cat'):\n        shutil.move(os.path.join(train_dir, fname), os.path.join(cat_dir, fname))\n    elif fname.startswith('dog'):\n        shutil.move(os.path.join(train_dir, fname), os.path.join(dog_dir, fname))\n\n# train_dir は不要になったので削除\nos.rmdir(train_dir)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-04T08:32:41.763510Z","iopub.execute_input":"2025-07-04T08:32:41.763805Z","iopub.status.idle":"2025-07-04T08:32:50.812896Z","shell.execute_reply.started":"2025-07-04T08:32:41.763783Z","shell.execute_reply":"2025-07-04T08:32:50.812370Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# データジェネレータ\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,\n    validation_split=0.2,  # 検証用に20%使う\n    horizontal_flip=True,\n    zoom_range=0.2,\n    rotation_range=15\n)\n\n# トレーニングとバリデーション用ジェネレータ\ntrain_generator = train_datagen.flow_from_directory(\n    base_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    base_dir,\n    target_size=(150, 150),\n    batch_size=32,\n    class_mode='binary',\n    subset='validation'\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-04T08:32:50.813941Z","iopub.execute_input":"2025-07-04T08:32:50.814181Z","iopub.status.idle":"2025-07-04T08:33:05.816310Z","shell.execute_reply.started":"2025-07-04T08:32:50.814156Z","shell.execute_reply":"2025-07-04T08:33:05.815775Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.applications.vgg16 import VGG16\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, Flatten\nfrom tensorflow.keras.optimizers import Adam\n\nbase_model = VGG16(weights='imagenet', include_top=False, input_shape=(150, 150, 3))\nbase_model.trainable = False \n\nmodel = Sequential([\n    base_model,\n    Flatten(),\n    Dense(256, activation='relu'),\n    Dropout(0.5),\n    Dense(1, activation='sigmoid') \n])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-04T08:33:11.109696Z","iopub.execute_input":"2025-07-04T08:33:11.109906Z","iopub.status.idle":"2025-07-04T08:33:11.374915Z","shell.execute_reply.started":"2025-07-04T08:33:11.109889Z","shell.execute_reply":"2025-07-04T08:33:11.374366Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model.compile(optimizer=Adam(learning_rate=1e-4),\n              loss='binary_crossentropy',\n              metrics=['accuracy'])\n\n\nhistory = model.fit(\n    train_generator,\n    epochs=5,\n    validation_data=validation_generator\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-04T08:33:51.963348Z","iopub.execute_input":"2025-07-04T08:33:51.963676Z","iopub.status.idle":"2025-07-04T08:33:52.056554Z","shell.execute_reply.started":"2025-07-04T08:33:51.963646Z","shell.execute_reply":"2025-07-04T08:33:52.055125Z"}},"outputs":[],"execution_count":null}]}