{"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":{"execution":{"iopub.status.busy":"2023-07-29T02:49:45.778633Z","iopub.execute_input":"2023-07-29T02:49:45.7792Z","iopub.status.idle":"2023-07-29T02:50:01.612354Z","shell.execute_reply.started":"2023-07-29T02:49:45.779152Z","shell.execute_reply":"2023-07-29T02:50:01.61121Z"},"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ランダムに画像を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":"2023-07-29T02:50:01.614584Z","iopub.execute_input":"2023-07-29T02:50:01.614954Z","iopub.status.idle":"2023-07-29T02:50:01.622359Z","shell.execute_reply.started":"2023-07-29T02:50:01.614921Z","shell.execute_reply":"2023-07-29T02:50:01.619692Z"},"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":"2023-07-29T02:50:01.623967Z","iopub.execute_input":"2023-07-29T02:50:01.624596Z","iopub.status.idle":"2023-07-29T02:50:04.465022Z","shell.execute_reply.started":"2023-07-29T02:50:01.624561Z","shell.execute_reply":"2023-07-29T02:50:04.463798Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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（メモリを抑える）\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)","metadata":{"execution":{"iopub.status.busy":"2023-07-29T02:50:04.466343Z","iopub.execute_input":"2023-07-29T02:50:04.466765Z","iopub.status.idle":"2023-07-29T02:51:40.648736Z","shell.execute_reply.started":"2023-07-29T02:50:04.466731Z","shell.execute_reply":"2023-07-29T02:51:40.647536Z"},"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":"2023-07-29T02:51:40.65255Z","iopub.execute_input":"2023-07-29T02:51:40.652992Z","iopub.status.idle":"2023-07-29T02:51:40.683911Z","shell.execute_reply.started":"2023-07-29T02:51:40.652955Z","shell.execute_reply":"2023-07-29T02:51:40.682793Z"},"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":"2023-07-29T02:51:40.685711Z","iopub.execute_input":"2023-07-29T02:51:40.686671Z","iopub.status.idle":"2023-07-29T02:51:40.70426Z","shell.execute_reply.started":"2023-07-29T02:51:40.686634Z","shell.execute_reply":"2023-07-29T02:51:40.702826Z"},"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":"2023-07-29T02:51:40.706259Z","iopub.execute_input":"2023-07-29T02:51:40.706708Z","iopub.status.idle":"2023-07-29T02:51:40.715979Z","shell.execute_reply.started":"2023-07-29T02:51:40.706673Z","shell.execute_reply":"2023-07-29T02:51:40.714908Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 分類学習\n事前学習済みモデルEfficientNetを使用","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":"2023-07-29T02:51:40.718033Z","iopub.execute_input":"2023-07-29T02:51:40.71841Z","iopub.status.idle":"2023-07-29T02:51:49.235627Z","shell.execute_reply.started":"2023-07-29T02:51:40.718378Z","shell.execute_reply":"2023-07-29T02:51:49.23456Z"},"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.EfficientNetB3(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":"2023-07-29T02:51:49.237708Z","iopub.execute_input":"2023-07-29T02:51:49.23883Z","iopub.status.idle":"2023-07-29T02:51:58.663007Z","shell.execute_reply.started":"2023-07-29T02:51:49.238747Z","shell.execute_reply":"2023-07-29T02:51:58.662007Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## データセットの生成","metadata":{}},{"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":"2023-07-29T02:51:58.664618Z","iopub.execute_input":"2023-07-29T02:51:58.665435Z","iopub.status.idle":"2023-07-29T02:52:00.581838Z","shell.execute_reply.started":"2023-07-29T02:51:58.665398Z","shell.execute_reply":"2023-07-29T02:52:00.580817Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"epoch数を5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 = 5,\n    callbacks = [checkpoint]\n)","metadata":{"execution":{"iopub.status.busy":"2023-07-29T02:52:00.583456Z","iopub.execute_input":"2023-07-29T02:52:00.583868Z","iopub.status.idle":"2023-07-29T03:19:06.466185Z","shell.execute_reply.started":"2023-07-29T02:52:00.58383Z","shell.execute_reply":"2023-07-29T03:19:06.465163Z"},"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":"2023-07-29T03:19:06.467699Z","iopub.execute_input":"2023-07-29T03:19:06.468054Z","iopub.status.idle":"2023-07-29T03:19:33.019888Z","shell.execute_reply.started":"2023-07-29T03:19:06.468028Z","shell.execute_reply":"2023-07-29T03:19:33.017708Z"},"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":"2023-07-29T03:19:33.021797Z","iopub.execute_input":"2023-07-29T03:19:33.022169Z","iopub.status.idle":"2023-07-29T03:19:33.324053Z","shell.execute_reply.started":"2023-07-29T03:19:33.022138Z","shell.execute_reply":"2023-07-29T03:19:33.323166Z"},"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":"2023-07-29T03:19:33.32798Z","iopub.execute_input":"2023-07-29T03:19:33.328263Z","iopub.status.idle":"2023-07-29T03:19:33.33522Z","shell.execute_reply.started":"2023-07-29T03:19:33.328238Z","shell.execute_reply":"2023-07-29T03:19:33.334074Z"},"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":"2023-07-29T03:19:33.337022Z","iopub.execute_input":"2023-07-29T03:19:33.338213Z","iopub.status.idle":"2023-07-29T03:19:33.348457Z","shell.execute_reply.started":"2023-07-29T03:19:33.338176Z","shell.execute_reply":"2023-07-29T03:19:33.347081Z"},"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":"2023-07-29T03:19:33.349645Z","iopub.execute_input":"2023-07-29T03:19:33.352031Z","iopub.status.idle":"2023-07-29T03:19:39.438635Z","shell.execute_reply.started":"2023-07-29T03:19:33.352002Z","shell.execute_reply":"2023-07-29T03:19:39.437467Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred = 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":"2023-07-29T03:19:39.441256Z","iopub.execute_input":"2023-07-29T03:19:39.442105Z","iopub.status.idle":"2023-07-29T03:20:24.10074Z","shell.execute_reply.started":"2023-07-29T03:19:39.442065Z","shell.execute_reply":"2023-07-29T03:20:24.099636Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv('submit_trained.csv')\ndf.head()","metadata":{"execution":{"iopub.status.busy":"2023-07-29T03:20:24.102183Z","iopub.execute_input":"2023-07-29T03:20:24.102849Z","iopub.status.idle":"2023-07-29T03:20:24.125704Z","shell.execute_reply.started":"2023-07-29T03:20:24.102805Z","shell.execute_reply":"2023-07-29T03:20:24.124808Z"},"trusted":true},"execution_count":null,"outputs":[]}]}