{"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":"# 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":"2023-07-25T11:51:22.792727Z","iopub.execute_input":"2023-07-25T11:51:22.793644Z","iopub.status.idle":"2023-07-25T11:51:22.828340Z","shell.execute_reply.started":"2023-07-25T11:51:22.793603Z","shell.execute_reply":"2023-07-25T11:51:22.827206Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import zipfile\n\n# train.zipの展開\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip', 'r') as zip_ref:\n    zip_ref.extractall('/kaggle/working/train')\n\n# test.zipの展開\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip', 'r') as zip_ref:\n    zip_ref.extractall('/kaggle/working/test')","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:22.830056Z","iopub.execute_input":"2023-07-25T11:51:22.830993Z","iopub.status.idle":"2023-07-25T11:51:41.578544Z","shell.execute_reply.started":"2023-07-25T11:51:22.830961Z","shell.execute_reply":"2023-07-25T11:51:41.577390Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ライブラリのインポート(globライブラリを用いてファイル検索)\nimport glob\n\n# ファイル一覧を取得\nimages = glob.glob('/kaggle/working/train/train/*.jpg')\n\n# ファイル名を確認(先頭3枚)\nprint(images[:3])","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:41.580202Z","iopub.execute_input":"2023-07-25T11:51:41.580629Z","iopub.status.idle":"2023-07-25T11:51:41.692472Z","shell.execute_reply.started":"2023-07-25T11:51:41.580586Z","shell.execute_reply":"2023-07-25T11:51:41.691309Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 画像表示に必要なモジュールをインポート\nimport matplotlib.pyplot as plt\nfrom PIL import Image\n\n# 画像の表示\nimage_sample = images[0]\nimg = Image.open(image_sample)\nprint('filename:{}, size:{}'.format(image_sample, img.size))\nplt.imshow(img)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:41.695109Z","iopub.execute_input":"2023-07-25T11:51:41.695432Z","iopub.status.idle":"2023-07-25T11:51:42.145003Z","shell.execute_reply.started":"2023-07-25T11:51:41.695403Z","shell.execute_reply":"2023-07-25T11:51:42.143999Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os \n\n# train用フォルダ作成\nos.makedirs('/kaggle/working/images/train/dog', exist_ok=True)\nos.makedirs('/kaggle/working/images/train/cat', exist_ok=True)\n\n# val用フォルダ作成\nos.makedirs('/kaggle/working/images/val/dog', exist_ok=True)\nos.makedirs('/kaggle/working/images/val/cat', exist_ok=True)\n\n# test用フォルダ作成\nos.makedirs('/kaggle/working/images/test/test', exist_ok=True)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:42.146245Z","iopub.execute_input":"2023-07-25T11:51:42.147052Z","iopub.status.idle":"2023-07-25T11:51:42.155185Z","shell.execute_reply.started":"2023-07-25T11:51:42.147020Z","shell.execute_reply":"2023-07-25T11:51:42.154041Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 犬・猫ごとのファイルパス一覧を取得\nimages_dog = glob.glob('/kaggle/working/train/train/dog.*.jpg')\nimages_cat = glob.glob('/kaggle/working/train/train/cat.*.jpg')\nimages_test = glob.glob('/kaggle/working/test/test/*.jpg')","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:42.156656Z","iopub.execute_input":"2023-07-25T11:51:42.157112Z","iopub.status.idle":"2023-07-25T11:51:42.372355Z","shell.execute_reply.started":"2023-07-25T11:51:42.157074Z","shell.execute_reply":"2023-07-25T11:51:42.371172Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ファイルを分割(train, val)\nidx_test_start = int(len(images_cat) * 0.8)\n\nimages_val_dog = images_dog[idx_test_start:]\nimages_val_cat = images_cat[idx_test_start:]\n\nimages_train_dog = images_dog[:idx_test_start]\nimages_train_cat = images_cat[:idx_test_start]","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:42.373837Z","iopub.execute_input":"2023-07-25T11:51:42.374273Z","iopub.status.idle":"2023-07-25T11:51:42.382081Z","shell.execute_reply.started":"2023-07-25T11:51:42.374232Z","shell.execute_reply":"2023-07-25T11:51:42.380894Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import shutil\n\n# 一括でファイルを移動する関数を作成\ndef move_files(file_list, target_dir):\n    for file in file_list:\n        shutil.move(file, target_dir)\n\n# ファイル移動\nmove_files(images_train_dog, '/kaggle/working/images/train/dog/')\nmove_files(images_train_cat, '/kaggle/working/images/train/cat/')\nmove_files(images_val_dog, '/kaggle/working/images/val/dog/')\nmove_files(images_val_cat, '/kaggle/working/images/val/cat/')\nmove_files(images_test, '/kaggle/working/images/test/test/')","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:42.383656Z","iopub.execute_input":"2023-07-25T11:51:42.384130Z","iopub.status.idle":"2023-07-25T11:51:44.444647Z","shell.execute_reply.started":"2023-07-25T11:51:42.384080Z","shell.execute_reply":"2023-07-25T11:51:44.443058Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#分類するクラス\nclasses = ['cat', 'dog']\nnb_classes = len(classes)\n \n# データのディレクトリ\ntrain_data_dir = '/kaggle/working/images/train'\nvalidation_data_dir = '/kaggle/working/images/val'\ntest_data_dir = '/kaggle/working/images/test'\n\n# 学習回数\nepochs = 1\n\n# バッチサイズ\nbatch_size = 1024\n\n# 画像サイズ\nimg_width, img_height = 224, 224","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:44.446534Z","iopub.execute_input":"2023-07-25T11:51:44.447032Z","iopub.status.idle":"2023-07-25T11:51:44.454583Z","shell.execute_reply.started":"2023-07-25T11:51:44.446988Z","shell.execute_reply":"2023-07-25T11:51:44.453088Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# 学習データのImageDataGenerator作成\ntrain_datagen = ImageDataGenerator(rescale=1.0 / 255)  # rescaleで各画素のスケールを0～255から0～1に変換\ntrain_generator = train_datagen.flow_from_directory(\n    directory=train_data_dir,\n    target_size=(img_width, img_height),\n    color_mode='rgb',\n    classes=classes,\n    class_mode='categorical',\n    batch_size=batch_size\n)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:44.458690Z","iopub.execute_input":"2023-07-25T11:51:44.459161Z","iopub.status.idle":"2023-07-25T11:51:55.045360Z","shell.execute_reply.started":"2023-07-25T11:51:44.459121Z","shell.execute_reply":"2023-07-25T11:51:55.044389Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 検証データのImageDataGenerator作成\nvalidation_datagen = ImageDataGenerator(rescale=1.0 / 255) \nvalidation_generator = validation_datagen.flow_from_directory(\n    directory=validation_data_dir,\n    target_size=(img_width, img_height),\n    color_mode='rgb',\n    classes=classes,\n    class_mode='categorical',\n    batch_size=batch_size\n)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:55.046750Z","iopub.execute_input":"2023-07-25T11:51:55.048368Z","iopub.status.idle":"2023-07-25T11:51:55.218007Z","shell.execute_reply.started":"2023-07-25T11:51:55.048318Z","shell.execute_reply":"2023-07-25T11:51:55.216628Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 評価データのImageDataGenerator作成\ntest_datagen = ImageDataGenerator(rescale=1.0 / 255) \ntest_generator = test_datagen.flow_from_directory(\n    directory=test_data_dir,\n    target_size=(img_width, img_height),\n    batch_size=64,\n    class_mode=None,\n    shuffle=False  # シャッフルしない\n)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:55.219521Z","iopub.execute_input":"2023-07-25T11:51:55.220300Z","iopub.status.idle":"2023-07-25T11:51:55.620583Z","shell.execute_reply.started":"2023-07-25T11:51:55.220267Z","shell.execute_reply":"2023-07-25T11:51:55.619346Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.applications.vgg16 import VGG16\nfrom tensorflow.keras.models import Sequential, Model\nfrom tensorflow.keras.layers import Input, Flatten, Dense\n\ninput_tensor = Input(shape=(img_width, img_height, 3))\nVGG16 = VGG16(include_top=False, weights='imagenet', input_tensor=input_tensor)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:55.622118Z","iopub.execute_input":"2023-07-25T11:51:55.622464Z","iopub.status.idle":"2023-07-25T11:51:59.925386Z","shell.execute_reply.started":"2023-07-25T11:51:55.622434Z","shell.execute_reply":"2023-07-25T11:51:59.924271Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# VGG16のパラメータを凍結(すべての層を凍結)\nfor layer in VGG16.layers:\n    layer.trainable = False ","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:59.926686Z","iopub.execute_input":"2023-07-25T11:51:59.927032Z","iopub.status.idle":"2023-07-25T11:51:59.933732Z","shell.execute_reply.started":"2023-07-25T11:51:59.927003Z","shell.execute_reply":"2023-07-25T11:51:59.932207Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 差し替え用の新しい層を追加\nmodel = Sequential()\nmodel.add(VGG16)\nmodel.add(Flatten())\nmodel.add(Dense(nb_classes, activation='softmax'))","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:51:59.935194Z","iopub.execute_input":"2023-07-25T11:51:59.935598Z","iopub.status.idle":"2023-07-25T11:52:00.049597Z","shell.execute_reply.started":"2023-07-25T11:51:59.935569Z","shell.execute_reply":"2023-07-25T11:52:00.048083Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.summary()","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:52:00.050943Z","iopub.execute_input":"2023-07-25T11:52:00.051268Z","iopub.status.idle":"2023-07-25T11:52:00.073132Z","shell.execute_reply.started":"2023-07-25T11:52:00.051240Z","shell.execute_reply":"2023-07-25T11:52:00.072262Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras import optimizers\n\nmodel.compile(loss='categorical_crossentropy',\n              optimizer=optimizers.Adam(learning_rate=1e-3),\n              metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:52:00.074129Z","iopub.execute_input":"2023-07-25T11:52:00.074446Z","iopub.status.idle":"2023-07-25T11:52:00.098317Z","shell.execute_reply.started":"2023-07-25T11:52:00.074419Z","shell.execute_reply":"2023-07-25T11:52:00.097116Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 学習\nsteps_per_epoch = int(len(train_generator.classes) / batch_size) \nhistory = model.fit(\n    x=train_generator,  # 学習データ\n    steps_per_epoch=steps_per_epoch,  # ステップ数\n    epochs=epochs,  # エポック数\n    validation_data=validation_generator  # 検証データ\n)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T11:52:00.099635Z","iopub.execute_input":"2023-07-25T11:52:00.099982Z","iopub.status.idle":"2023-07-25T13:46:26.313731Z","shell.execute_reply.started":"2023-07-25T11:52:00.099953Z","shell.execute_reply":"2023-07-25T13:46:26.312563Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# グラフ描画(2画面)\nplt.figure(figsize=(8, 4))\n\n# epochごとのlossを表示\nplt.subplot(1, 2, 1)\nplt.plot(range(1, epochs+1), history.history['loss'], '-o')\nplt.plot(range(1, epochs+1), history.history['val_loss'], '-o')\nplt.title('loss_transition')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.grid()\nplt.legend(['loss', 'val_loss'], loc='best')\n\n# epochごとのaccuracyを表示\nplt.subplot(1, 2, 2)\nplt.plot(range(1, epochs+1), history.history['accuracy'], '-o')\nplt.plot(range(1, epochs+1), history.history['val_accuracy'], '-o')\nplt.title('accuracy_transition')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.grid()\nplt.legend(['accuracy', 'val_accuracy'], loc='best')\n\n# グラフ表示\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-25T13:46:26.315722Z","iopub.execute_input":"2023-07-25T13:46:26.316118Z","iopub.status.idle":"2023-07-25T13:46:26.886075Z","shell.execute_reply.started":"2023-07-25T13:46:26.316073Z","shell.execute_reply":"2023-07-25T13:46:26.884880Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.evaluate(test_generator)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T13:46:26.888049Z","iopub.execute_input":"2023-07-25T13:46:26.888516Z","iopub.status.idle":"2023-07-25T13:47:07.708797Z","shell.execute_reply.started":"2023-07-25T13:46:26.888452Z","shell.execute_reply":"2023-07-25T13:47:07.707598Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 正解のラベル一覧を作成。\ntrue = test_generator.classes\ntrue","metadata":{"execution":{"iopub.status.busy":"2023-07-25T13:47:07.710508Z","iopub.execute_input":"2023-07-25T13:47:07.710919Z","iopub.status.idle":"2023-07-25T13:47:07.719787Z","shell.execute_reply.started":"2023-07-25T13:47:07.710885Z","shell.execute_reply":"2023-07-25T13:47:07.718497Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 予測のラベル一覧を作成\nimport numpy as np\np = model.predict(test_generator)\npred = np.argmax(p, axis=1)\npred","metadata":{"execution":{"iopub.status.busy":"2023-07-25T13:47:07.721244Z","iopub.execute_input":"2023-07-25T13:47:07.721748Z","iopub.status.idle":"2023-07-25T14:47:30.146875Z","shell.execute_reply.started":"2023-07-25T13:47:07.721703Z","shell.execute_reply":"2023-07-25T14:47:30.144212Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 混同行列表示\n#from tensorflow.math import confusion_matrix\n#confusion_matrix(true, pred)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T14:47:30.150900Z","iopub.execute_input":"2023-07-25T14:47:30.151696Z","iopub.status.idle":"2023-07-25T14:47:30.159546Z","shell.execute_reply.started":"2023-07-25T14:47:30.151659Z","shell.execute_reply":"2023-07-25T14:47:30.158215Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred_pd = pd.DataFrame(p)\n# id列を作成\npred_pd.insert(0, 'id', range(1, len(pred_pd) + 1))\npred_pd.columns\npred_pd = pred_pd.drop([0], axis=1)\npred_pd = pred_pd.rename(columns={1: 'label'})\npred_pd","metadata":{"execution":{"iopub.status.busy":"2023-07-25T14:47:30.161148Z","iopub.execute_input":"2023-07-25T14:47:30.161540Z","iopub.status.idle":"2023-07-25T14:47:30.226853Z","shell.execute_reply.started":"2023-07-25T14:47:30.161508Z","shell.execute_reply":"2023-07-25T14:47:30.225429Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv('/kaggle/input/dogs-vs-cats-redux-kernels-edition/sample_submission.csv') # ひな形ファイルを読み込む\nprint(sub.shape)\n# subのlabel列をtest_predictedのlabel列で上書きする\nsub['label'] = pred_pd['label']\n# 結果を表示\nsub\nsub.to_csv('submission.csv', index=False) # 変換したファイルを保存","metadata":{"execution":{"iopub.status.busy":"2023-07-25T14:47:30.228596Z","iopub.execute_input":"2023-07-25T14:47:30.229434Z","iopub.status.idle":"2023-07-25T14:47:30.319418Z","shell.execute_reply.started":"2023-07-25T14:47:30.229395Z","shell.execute_reply":"2023-07-25T14:47:30.318185Z"},"trusted":true},"execution_count":null,"outputs":[]}]}