{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import zipfile\nimport glob\nimport os\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport collections\n\nfrom PIL import Image\n\ntrain_dir = 'train'\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip', 'r') as train_zip:\n    train_zip.extractall('')\n\ntrain_list = glob.glob(os.path.join(train_dir,'*.jpg'))\nprint(f\"Train Data: {len(train_list)}\")\n\nbase_dir = '/kaggle/working'\ntrain_dir = os.path.join(base_dir, 'train')\n\ntest_dir = 'test'\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip', 'r') as test_zip:\n    test_zip.extractall('')\n\ntest_list = glob.glob(os.path.join(test_dir,'*.jpg'))\nprint(f\"Test Data: {len(test_list)}\")\n\nbase_dir = '/kaggle/working'\ntest_dir = os.path.join(base_dir, 'test')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-07-21T07:43:29.425109Z","iopub.execute_input":"2023-07-21T07:43:29.425502Z","iopub.status.idle":"2023-07-21T07:43:41.774690Z","shell.execute_reply.started":"2023-07-21T07:43:29.425469Z","shell.execute_reply":"2023-07-21T07:43:41.773702Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## ダウンロードしたデータを確認する\n画像ランダムに9つ表示","metadata":{}},{"cell_type":"code","source":"print(f'学習データ数：{len(train_list)}', f'先頭のデータ：{train_list[0]}')\nprint(f'テストデータ数：{len(test_list)}', f'先頭のデータ：{test_list[0]}')","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:43:41.776773Z","iopub.execute_input":"2023-07-21T07:43:41.777494Z","iopub.status.idle":"2023-07-21T07:43:41.783485Z","shell.execute_reply.started":"2023-07-21T07:43:41.777456Z","shell.execute_reply":"2023-07-21T07:43:41.782308Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"labels = [path.split('/')[-1].split('.')[0] for path in train_list]\n\nrandom_idx = np.random.randint(1, len(train_list), size=9)\nfig, axes = plt.subplots(3, 3, figsize=(16, 12))\n\nfor idx, ax in enumerate(axes.ravel()):\n    img = Image.open(train_list[idx])\n    img_r = img.transpose(Image.FLIP_LEFT_RIGHT)\n    ax.set_title(labels[idx])\n    ax.imshow(img_r)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:43:41.785469Z","iopub.execute_input":"2023-07-21T07:43:41.786188Z","iopub.status.idle":"2023-07-21T07:43:44.507695Z","shell.execute_reply.started":"2023-07-21T07:43:41.786156Z","shell.execute_reply":"2023-07-21T07:43:44.506803Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"2次元上にプロット\n赤：Dog\n青：Cat","metadata":{}},{"cell_type":"markdown","source":"## 学習データ・テストデータ・検証データの生成","metadata":{}},{"cell_type":"code","source":"#from PIL import Image\n#import os, glob\n#import numpy as np\nfrom PIL import ImageFile\nfrom sklearn.model_selection import train_test_split\n\nclasses = {'dog':0, 'cat':1}\nimage_size = 224 #推奨224\ndim = 1 # option\n\nX_train = []\ny_train = []\nX_test  = []\n\ntrain_labels = [path.split('/')[-1].split('.')[0] for path in train_list]\n\nfor i, img in enumerate(train_list) :\n    image = Image.open(img)\n    image = image.convert(\"L\") #グレースケール　本来はRGB\n    image = image.resize((image_size, image_size))\n    data = np.asarray(image)\n    X_train.append(data)\n    y_train.append(classes[train_labels[i]])\n    \nfor i, img in enumerate(test_list) :\n    image = Image.open(img)\n    image = image.convert(\"L\")\n    image = image.resize((image_size, image_size))\n    data = np.asarray(image)\n    X_test.append(data)\n\nX_train = np.array(X_train)\ny_train = np.array(y_train)\nX_train, X_val, y_train, y_val = train_test_split(X_train, y_train, train_size=0.7, random_state=0)\n\nX_test  = np.array(X_test)\n","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:43:44.510315Z","iopub.execute_input":"2023-07-21T07:43:44.510891Z","iopub.status.idle":"2023-07-21T07:45:21.408189Z","shell.execute_reply.started":"2023-07-21T07:43:44.510854Z","shell.execute_reply":"2023-07-21T07:45:21.407075Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"生成データの確認","metadata":{}},{"cell_type":"code","source":"print('学習・検証・テストデータ')\nprint(f'学習データ数：{len(X_train)} 検証データ数:{len(X_val)} テストデータ数：{len(X_test)}')\nprint(f'学習ラベル数：{len(y_train)} 検証ラベル数:{len(y_val)}')\nprint('1つのデータ')\nprint(f'学習の次元数：{X_train[0].shape} 検証の次元数：{X_val[0].shape} テストの次元数：{X_test[0].shape}')\nprint(f'学習ラベル：{y_train[0]} 検証ラベル：{y_val[0]}')\n# メモリ確保のため変数の削除\ndel train_list\ndel train_labels\ndel image\ndel data","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:45:21.410089Z","iopub.execute_input":"2023-07-21T07:45:21.410481Z","iopub.status.idle":"2023-07-21T07:45:21.418602Z","shell.execute_reply.started":"2023-07-21T07:45:21.410447Z","shell.execute_reply":"2023-07-21T07:45:21.417392Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"ラベル分布","metadata":{}},{"cell_type":"code","source":"import collections\nc1 = collections.Counter(y_train)\nc2 = collections.Counter(y_val)\nprint(classes)\nprint(f'学習データのラベル分布：{c1}')\nprint(f'検証データのラベル分布：{c2}')","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:45:21.420400Z","iopub.execute_input":"2023-07-21T07:45:21.421186Z","iopub.status.idle":"2023-07-21T07:45:21.438802Z","shell.execute_reply.started":"2023-07-21T07:45:21.421151Z","shell.execute_reply":"2023-07-21T07:45:21.437849Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('学習・検証・テストデータ')\nprint(f'学習データ数：{len(X_train)} 検証データ数:{len(X_val)} テストデータ数：{len(X_test)}')\nprint(f'学習ラベル数：{len(y_train)} 検証ラベル数:{len(y_val)}')\nprint('1つのデータ')\nprint(f'学習の次元数：{X_train[0].shape} 検証の次元数：{X_val[0].shape} テストの次元数：{X_test[0].shape}')\nprint(f'学習ラベル：{y_train[0]} 検証ラベル：{y_val[0]}')","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:45:21.440093Z","iopub.execute_input":"2023-07-21T07:45:21.440973Z","iopub.status.idle":"2023-07-21T07:45:21.459574Z","shell.execute_reply.started":"2023-07-21T07:45:21.440938Z","shell.execute_reply":"2023-07-21T07:45:21.458444Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 分類学習\nモデル構築\n\n事前学習モデルを呼び出す","metadata":{}},{"cell_type":"code","source":"from keras.models import Sequential ,Model\nfrom keras.layers import Conv2D, MaxPooling2D\nfrom keras.layers import Input, Activation, Dropout, Flatten, Dense\nfrom keras.optimizers import RMSprop\nimport tensorflow as tf\n\nimport keras\nimport numpy as np","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:45:21.460904Z","iopub.execute_input":"2023-07-21T07:45:21.461332Z","iopub.status.idle":"2023-07-21T07:45:36.274190Z","shell.execute_reply.started":"2023-07-21T07:45:21.461298Z","shell.execute_reply":"2023-07-21T07:45:36.273213Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_model(image_size, num_classes):\n    # 画像を受け取る層\n    inputs = Input(shape = image_size)\n    # EfficientNetB3を作成\n    x = tf.keras.applications.efficientnet.EfficientNetB0(include_top = False)(inputs)\n    # １次元に変換する層\n    x = Flatten()(x)\n    # 最終出力層\n    outputs = Dense(units = num_classes, activation = \"softmax\")(x)\n\n    # 定義した層を使ってモデル作成\n    model = Model(inputs = inputs, outputs = outputs)\n    # 最適化手法と損失関数を定義\n    model.compile(\n        optimizer = tf.keras.optimizers.Adam(learning_rate = 5e-5),\n        loss = \"sparse_categorical_crossentropy\",\n        metrics=['accuracy']\n    )\n    return model\n\n# モデルの呼び出し\ntf.keras.backend.clear_session()\nmodel = get_model((image_size, image_size, dim), 2)\n#model = get_model(X_train.shape[-3:], 2)\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:45:36.275498Z","iopub.execute_input":"2023-07-21T07:45:36.276761Z","iopub.status.idle":"2023-07-21T07:45:45.892643Z","shell.execute_reply.started":"2023-07-21T07:45:36.276721Z","shell.execute_reply":"2023-07-21T07:45:45.891613Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## データセットの生成","metadata":{}},{"cell_type":"code","source":"'''\ntrain_dataset = tf.data.Dataset.from_tensor_slices((X_train, y_train))\ntest_dataset = tf.data.Dataset.from_tensor_slices((X_val, y_val))\n\ntrain_dataset = train_dataset.batch(32)\ntest_dataset = test_dataset.batch(32)\n\ntrain_dataset = train_dataset.shuffle(1024 * 50)\n\nbatch = next(iter(train_dataset))\nprint(batch[0].shape)\nprint(batch[1].shape)\n'''","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:45:45.896458Z","iopub.execute_input":"2023-07-21T07:45:45.896744Z","iopub.status.idle":"2023-07-21T07:45:45.904026Z","shell.execute_reply.started":"2023-07-21T07:45:45.896718Z","shell.execute_reply":"2023-07-21T07:45:45.902999Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 分類モデルへの入力データ用の作成\nBATCH_SIZE = 32 # 学習バッチサイズ\n\ntrain_dataset = tf.data.Dataset.from_tensor_slices((X_train, y_train)).batch(BATCH_SIZE)\n# メモリ確保のため変数の削除\ndel X_train\ndel y_train\n\ntest_dataset = tf.data.Dataset.from_tensor_slices((X_val, y_val)).batch(BATCH_SIZE)\ndel X_val # メモリ確保のため変数の削除\n\ntrain_dataset = train_dataset.shuffle(12345)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:45:45.905625Z","iopub.execute_input":"2023-07-21T07:45:45.906282Z","iopub.status.idle":"2023-07-21T07:45:48.341260Z","shell.execute_reply.started":"2023-07-21T07:45:45.906247Z","shell.execute_reply":"2023-07-21T07:45:48.340181Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"epoch数を10で学習","metadata":{}},{"cell_type":"code","source":"checkpoint = tf.keras.callbacks.ModelCheckpoint(\n    \"best_weight.h5\",     # ファイル名\n    monitor = \"val_loss\", # 参照するloss\n    mode = \"min\",         # monitorが最小のときに保存\n    save_best_only = True,\n    save_weights_only = True\n)\n\nhistory = model.fit(\n    train_dataset,\n    validation_data = test_dataset,\n    epochs = 10,\n    callbacks = [checkpoint]\n)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:45:48.343110Z","iopub.execute_input":"2023-07-21T07:45:48.343873Z","iopub.status.idle":"2023-07-21T08:12:37.993622Z","shell.execute_reply.started":"2023-07-21T07:45:48.343834Z","shell.execute_reply":"2023-07-21T08:12:37.992463Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.load_weights(\"best_weight.h5\")\npreds = model.predict(test_dataset)\nprint(preds[0])\nprint(y_val[0])","metadata":{"execution":{"iopub.status.busy":"2023-07-21T08:12:37.996848Z","iopub.execute_input":"2023-07-21T08:12:37.997516Z","iopub.status.idle":"2023-07-21T08:12:51.942836Z","shell.execute_reply.started":"2023-07-21T08:12:37.997478Z","shell.execute_reply":"2023-07-21T08:12:51.941710Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.plot(history.history[\"loss\"], label = \"train\")\nplt.plot(history.history[\"val_loss\"], label = \"valid\")\nplt.legend()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-21T08:12:51.944765Z","iopub.execute_input":"2023-07-21T08:12:51.945225Z","iopub.status.idle":"2023-07-21T08:12:52.216906Z","shell.execute_reply.started":"2023-07-21T08:12:51.945185Z","shell.execute_reply":"2023-07-21T08:12:52.215976Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred_labels = preds.argmax(axis = 1)\nprint(pred_labels[:5])\nprint(y_val[:5].reshape(-1))","metadata":{"execution":{"iopub.status.busy":"2023-07-21T08:12:52.218247Z","iopub.execute_input":"2023-07-21T08:12:52.219383Z","iopub.status.idle":"2023-07-21T08:12:52.225848Z","shell.execute_reply.started":"2023-07-21T08:12:52.219345Z","shell.execute_reply":"2023-07-21T08:12:52.224772Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import accuracy_score\n\nprint(accuracy_score(pred_labels, y_val.reshape(-1)))","metadata":{"execution":{"iopub.status.busy":"2023-07-21T08:12:52.227326Z","iopub.execute_input":"2023-07-21T08:12:52.227915Z","iopub.status.idle":"2023-07-21T08:12:52.242335Z","shell.execute_reply.started":"2023-07-21T08:12:52.227882Z","shell.execute_reply":"2023-07-21T08:12:52.241344Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## submitデータの作成","metadata":{}},{"cell_type":"code","source":"# モデルの呼び出し\ntf.keras.backend.clear_session()\nmodel = get_model((image_size, image_size, dim), 2)\nmodel.load_weights(\"best_weight.h5\")","metadata":{"execution":{"iopub.status.busy":"2023-07-21T08:12:52.244058Z","iopub.execute_input":"2023-07-21T08:12:52.244733Z","iopub.status.idle":"2023-07-21T08:12:55.753974Z","shell.execute_reply.started":"2023-07-21T08:12:52.244697Z","shell.execute_reply":"2023-07-21T08:12:55.752729Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"'''\npred = model.predict(X_test)\n\nimport pandas as pd\n\ndf1 = pd.DataFrame(pred, columns=['dog', 'cat'])\n\nids = [path.split('/')[-1].split('.')[0] for path in test_list]\nsubmit = list(zip(ids, df1['dog'].to_list()))\ndf2 = pd.DataFrame(submit, columns=['id', 'label'])\nprint(df2.head())\ndf2.to_csv('submit_trained.csv', index=False)\n'''\npred = model.predict(X_test)\n\nimport pandas as pd\n\ndf1 = pd.DataFrame(pred, columns=['dog', 'cat'])\nids = [path.split('/')[-1].split('.')[0] for path in test_list]\nsubmit = list(zip(ids, df1['dog'].to_list()))\ndf2 = pd.DataFrame(submit, columns=['id', 'label'])\nprint(df2.head())\ndf2.to_csv('submit_trained.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T08:12:55.767003Z","iopub.execute_input":"2023-07-21T08:12:55.767352Z","iopub.status.idle":"2023-07-21T08:13:19.674186Z","shell.execute_reply.started":"2023-07-21T08:12:55.767324Z","shell.execute_reply":"2023-07-21T08:13:19.673168Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv('submit_trained.csv')\ndf.head()","metadata":{"execution":{"iopub.status.busy":"2023-07-21T08:13:19.675825Z","iopub.execute_input":"2023-07-21T08:13:19.676585Z","iopub.status.idle":"2023-07-21T08:13:19.700098Z","shell.execute_reply.started":"2023-07-21T08:13:19.676547Z","shell.execute_reply":"2023-07-21T08:13:19.699086Z"},"trusted":true},"execution_count":null,"outputs":[]}]}