{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","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":31089,"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":"2025-07-18T09:09:20.478956Z","iopub.execute_input":"2025-07-18T09:09:20.479976Z","iopub.status.idle":"2025-07-18T09:09:20.487091Z","shell.execute_reply.started":"2025-07-18T09:09:20.479942Z","shell.execute_reply":"2025-07-18T09:09:20.486196Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport zipfile\nimport shutil\nimport random\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.applications import DenseNet121\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Dense, GlobalAveragePooling2D\nfrom tensorflow.keras.optimizers import RMSprop\n\n# =======================\n# 1. zipファイルを解凍\n# =======================\ninput_dir = \"/kaggle/input/dogs-vs-cats-redux-kernels-edition/\"\nwork_dir = \"/kaggle/working/\"\n\nwith zipfile.ZipFile(input_dir + \"train.zip\", \"r\") as zip_ref:\n    zip_ref.extractall(work_dir + \"train/\")\n\nwith zipfile.ZipFile(input_dir + \"test.zip\", \"r\") as zip_ref:\n    zip_ref.extractall(work_dir + \"test/\")\n\n# =======================\n# 2. データセットの整理\n# =======================\n# trainフォルダ構成: train/cat.123.jpg, dog.456.jpg\noriginal_train_dir = os.path.join(work_dir, \"train\", \"train\")  # zipの中に 'train/' サブフォルダがある\nbase_dir = os.path.join(work_dir, \"data_split\")\ntrain_dir = os.path.join(base_dir, \"train\")\nval_dir = os.path.join(base_dir, \"val\")\n\nfor split in [train_dir, val_dir]:\n    os.makedirs(os.path.join(split, \"cats\"), exist_ok=True)\n    os.makedirs(os.path.join(split, \"dogs\"), exist_ok=True)\n\n# 画像ファイルをラベルごとに分割\nfilenames = os.listdir(original_train_dir)\ncat_files = [f for f in filenames if f.startswith('cat')]\ndog_files = [f for f in filenames if f.startswith('dog')]\n\nrandom.seed(42)\nrandom.shuffle(cat_files)\nrandom.shuffle(dog_files)\n\n# 2000 train / 1000 val for each class\nfor i, fname in enumerate(cat_files):\n    src = os.path.join(original_train_dir, fname)\n    if i < 2000:\n        dst = os.path.join(train_dir, \"cats\", fname)\n    elif i < 3000:\n        dst = os.path.join(val_dir, \"cats\", fname)\n    shutil.copy(src, dst)\n\nfor i, fname in enumerate(dog_files):\n    src = os.path.join(original_train_dir, fname)\n    if i < 2000:\n        dst = os.path.join(train_dir, \"dogs\", fname)\n    elif i < 3000:\n        dst = os.path.join(val_dir, \"dogs\", fname)\n    shutil.copy(src, dst)\n\n# =======================\n# 3. データジェネレータの定義\n# =======================\ntrain_datagen = ImageDataGenerator(rescale=1./255,\n                                   rotation_range=20,\n                                   width_shift_range=0.1,\n                                   height_shift_range=0.1,\n                                   zoom_range=0.2,\n                                   horizontal_flip=True)\n\nval_datagen = ImageDataGenerator(rescale=1./255)\n\ntrain_gen = train_datagen.flow_from_directory(\n    train_dir,\n    target_size=(150, 150),\n    batch_size=32,\n    class_mode='binary'\n)\n\nval_gen = val_datagen.flow_from_directory(\n    val_dir,\n    target_size=(150, 150),\n    batch_size=32,\n    class_mode='binary'\n)\n\n# =======================\n# 4. DenseNetモデル構築\n# =======================\nbase_model = DenseNet121(weights='imagenet', include_top=False, input_shape=(150,150,3))\nbase_model.trainable = False\n\nx = base_model.output\nx = GlobalAveragePooling2D()(x)\nx = Dense(128, activation='relu')(x)\noutput = Dense(1, activation='sigmoid')(x)\n\nmodel = Model(inputs=base_model.input, outputs=output)\nmodel.compile(optimizer=RMSprop(learning_rate=1e-4),\n              loss='binary_crossentropy',\n              metrics=['accuracy'])\n\n# =======================\n# 5. 学習\n# =======================\nhistory = model.fit(\n    train_gen,\n    epochs=3,\n    validation_data=val_gen\n)\n\n# =======================\n# 6. 学習過程を可視化\n# =======================\nplt.plot(history.history['accuracy'], label='Train acc')\nplt.plot(history.history['val_accuracy'], label='Val acc')\nplt.title('Accuracy')\nplt.legend()\nplt.show()\n\n# =======================\n# 7. テスト画像を予測\n# =======================\ntest_dir = os.path.join(work_dir, \"test\", \"test\")  # 解凍後のパス\ntest_files = os.listdir(test_dir)\ntest_df = pd.DataFrame({'filename': test_files})\n\ntest_datagen = ImageDataGenerator(rescale=1./255)\ntest_generator = test_datagen.flow_from_dataframe(\n    test_df,\n    test_dir,\n    x_col='filename',\n    y_col=None,\n    class_mode=None,\n    target_size=(150,150),\n    batch_size=32,\n    shuffle=False\n)\n\npreds = model.predict(test_generator)\ntest_df['label'] = preds\ntest_df['label'] = test_df['label'].apply(lambda x: 1 if x > 0.5 else 0)\n\n# =======================\n# 8. 提出用ファイル生成\n# =======================\nsubmission = pd.DataFrame({\n    'id': test_df['filename'].str.extract('(\\d+)')[0].astype(int),\n    'label': test_df['label']\n})\nsubmission = submission.sort_values('id')\nsubmission.to_csv('/kaggle/working/submission.csv', index=False)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-18T09:11:59.234551Z","iopub.execute_input":"2025-07-18T09:11:59.235317Z","iopub.status.idle":"2025-07-18T09:30:07.416135Z","shell.execute_reply.started":"2025-07-18T09:11:59.235284Z","shell.execute_reply":"2025-07-18T09:30:07.415360Z"}},"outputs":[],"execution_count":null}]}