{"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":"2023-07-25T23:32:16.018206Z","iopub.execute_input":"2023-07-25T23:32:16.018888Z","iopub.status.idle":"2023-07-25T23:32:16.027672Z","shell.execute_reply.started":"2023-07-25T23:32:16.018858Z","shell.execute_reply":"2023-07-25T23:32:16.026440Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 必要なライブラリをインポート","metadata":{}},{"cell_type":"code","source":"from tensorflow import keras\nfrom keras.applications.vgg16 import VGG16\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten\nfrom keras.callbacks import ModelCheckpoint\nfrom matplotlib import pyplot as plt\nimport shutil\nimport os\nimport glob","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:32:23.645624Z","iopub.execute_input":"2023-07-25T23:32:23.645978Z","iopub.status.idle":"2023-07-25T23:32:23.651937Z","shell.execute_reply.started":"2023-07-25T23:32:23.645949Z","shell.execute_reply":"2023-07-25T23:32:23.650828Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Zipファイルを解凍","metadata":{}},{"cell_type":"code","source":"shutil.unpack_archive('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip', '/kaggle/working')\nshutil.unpack_archive('/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip', '/kaggle/working')\n\n\nshutil.copyfile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/sample_submission.csv','/kaggle/working/sample_submission.csv')\n\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n        \nfiles = glob.glob('/kaggle/working/*')\nfor file in files:\n    print(file)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:32:35.756360Z","iopub.execute_input":"2023-07-25T23:32:35.756729Z","iopub.status.idle":"2023-07-25T23:32:51.638572Z","shell.execute_reply.started":"2023-07-25T23:32:35.756700Z","shell.execute_reply":"2023-07-25T23:32:51.637628Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" # 画像サイズとディレクトリの設定","metadata":{}},{"cell_type":"code","source":"img_width, img_height = 150, 150\ntrain_dir = '/kaggle/working/train'\ntest_dir = '/kaggle/working/test'","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:33:05.139666Z","iopub.execute_input":"2023-07-25T23:33:05.140038Z","iopub.status.idle":"2023-07-25T23:33:05.145285Z","shell.execute_reply.started":"2023-07-25T23:33:05.140007Z","shell.execute_reply":"2023-07-25T23:33:05.144108Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# エポック数の設定","metadata":{}},{"cell_type":"code","source":"epoch = 20","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:33:53.002521Z","iopub.execute_input":"2023-07-25T23:33:53.002896Z","iopub.status.idle":"2023-07-25T23:33:53.007381Z","shell.execute_reply.started":"2023-07-25T23:33:53.002867Z","shell.execute_reply":"2023-07-25T23:33:53.006345Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 分類クラス名の設定","metadata":{}},{"cell_type":"code","source":"classes = ['dog','cat']\nnb_classes = len(classes)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:33:58.948830Z","iopub.execute_input":"2023-07-25T23:33:58.949209Z","iopub.status.idle":"2023-07-25T23:33:58.953873Z","shell.execute_reply.started":"2023-07-25T23:33:58.949178Z","shell.execute_reply":"2023-07-25T23:33:58.952845Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# VGG16モデルのロード","metadata":{}},{"cell_type":"code","source":"vgg_model = VGG16(include_top = False, weights = 'imagenet', input_shape = (img_height, img_width, 3))","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:34:18.915306Z","iopub.execute_input":"2023-07-25T23:34:18.915836Z","iopub.status.idle":"2023-07-25T23:34:25.036794Z","shell.execute_reply.started":"2023-07-25T23:34:18.915798Z","shell.execute_reply":"2023-07-25T23:34:25.035748Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# VGG16モデルの下に全結合層を追加","metadata":{}},{"cell_type":"code","source":"model = Sequential()\nmodel.add(vgg_model)\nmodel.add(Flatten())\nmodel.add(Dense(256, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(nb_classes, activation='softmax'))","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:34:55.166454Z","iopub.execute_input":"2023-07-25T23:34:55.166813Z","iopub.status.idle":"2023-07-25T23:34:55.284576Z","shell.execute_reply.started":"2023-07-25T23:34:55.166783Z","shell.execute_reply":"2023-07-25T23:34:55.283576Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# VGG16モデルの上位15層のパラメータを凍結(Fine tuning)","metadata":{}},{"cell_type":"code","source":"for layer in vgg_model.layers[:15]:\n layer.trainable = False","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:35:12.342002Z","iopub.execute_input":"2023-07-25T23:35:12.342368Z","iopub.status.idle":"2023-07-25T23:35:12.348431Z","shell.execute_reply.started":"2023-07-25T23:35:12.342339Z","shell.execute_reply":"2023-07-25T23:35:12.347138Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# モデルの詳細を表示","metadata":{}},{"cell_type":"code","source":"model.summary()","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:35:29.313613Z","iopub.execute_input":"2023-07-25T23:35:29.313966Z","iopub.status.idle":"2023-07-25T23:35:29.344839Z","shell.execute_reply.started":"2023-07-25T23:35:29.313936Z","shell.execute_reply":"2023-07-25T23:35:29.344095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 損失関数は交差エントロピー、最適化関数は確率的勾配法\n","metadata":{}},{"cell_type":"code","source":"model.compile(loss = 'categorical_crossentropy', optimizer = 'sgd', metrics = ['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:35:56.272847Z","iopub.execute_input":"2023-07-25T23:35:56.273218Z","iopub.status.idle":"2023-07-25T23:35:56.295840Z","shell.execute_reply.started":"2023-07-25T23:35:56.273188Z","shell.execute_reply":"2023-07-25T23:35:56.294979Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 犬・猫の画像を，それぞれ保存するフォルダのパスを定義","metadata":{}},{"cell_type":"code","source":"dog_dir = '/kaggle/working/train/dog'\ncat_dir = '/kaggle/working/train/cat'\n\nos.makedirs(dog_dir, exist_ok = True)\nos.makedirs(cat_dir, exist_ok = True)\n","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:36:19.435486Z","iopub.execute_input":"2023-07-25T23:36:19.435845Z","iopub.status.idle":"2023-07-25T23:36:19.441857Z","shell.execute_reply.started":"2023-07-25T23:36:19.435815Z","shell.execute_reply":"2023-07-25T23:36:19.440616Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 犬・猫の画像をそれぞれのフォルダに移動  \n# 訓練用フォルダ内の全ファイルパスを取得","metadata":{}},{"cell_type":"code","source":"files = glob.glob('/kaggle/working/train/*.jpg')\nfor file in files:\n    file_name = os.path.basename(file)\n    if 'cat' in file:\n        shutil.move(file,'/kaggle/working/train/cat/' + file_name)\n    else:\n        shutil.move(file,'/kaggle/working/train/dog/' + file_name)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:36:35.622644Z","iopub.execute_input":"2023-07-25T23:36:35.623030Z","iopub.status.idle":"2023-07-25T23:36:36.534312Z","shell.execute_reply.started":"2023-07-25T23:36:35.622998Z","shell.execute_reply":"2023-07-25T23:36:36.533311Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 学習データのデータ拡張を設定","metadata":{}},{"cell_type":"code","source":"train_datagen = ImageDataGenerator(rescale = 1.0 / 255, rotation_range = 90, shear_range = 0.2, zoom_range = 0.2, horizontal_flip = True,\n                vertical_flip = True, fill_mode = 'reflect', validation_split = 0.2)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:36:55.435186Z","iopub.execute_input":"2023-07-25T23:36:55.435698Z","iopub.status.idle":"2023-07-25T23:36:55.441631Z","shell.execute_reply.started":"2023-07-25T23:36:55.435661Z","shell.execute_reply":"2023-07-25T23:36:55.440823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 評価データのデータ拡張を設定","metadata":{}},{"cell_type":"code","source":"test_datagen = ImageDataGenerator(rescale = 1.0 / 255)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:37:34.241827Z","iopub.execute_input":"2023-07-25T23:37:34.242198Z","iopub.status.idle":"2023-07-25T23:37:34.246780Z","shell.execute_reply.started":"2023-07-25T23:37:34.242168Z","shell.execute_reply":"2023-07-25T23:37:34.245519Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 学習データのジェネレータを生成","metadata":{}},{"cell_type":"code","source":"train_generator = train_datagen.flow_from_directory(train_dir, target_size = (img_height, img_width), classes = classes, batch_size = 32, class_mode = 'categorical', subset = \"training\")","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:37:56.201515Z","iopub.execute_input":"2023-07-25T23:37:56.202872Z","iopub.status.idle":"2023-07-25T23:37:56.755811Z","shell.execute_reply.started":"2023-07-25T23:37:56.202818Z","shell.execute_reply":"2023-07-25T23:37:56.754886Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 評価データのジェネレータを生成","metadata":{}},{"cell_type":"code","source":"test_generator = train_datagen.flow_from_directory(train_dir, target_size = (img_height, img_width), classes = classes, batch_size = 32, class_mode = 'categorical', subset = \"validation\")","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:38:15.027027Z","iopub.execute_input":"2023-07-25T23:38:15.027412Z","iopub.status.idle":"2023-07-25T23:38:15.252246Z","shell.execute_reply.started":"2023-07-25T23:38:15.027382Z","shell.execute_reply":"2023-07-25T23:38:15.251342Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# コールバック関数(モデル保存)の設定","metadata":{}},{"cell_type":"code","source":"mc_cb = ModelCheckpoint(filepath = 'finetuning.h5', monitor = 'vol_loss', verbose = 1, save_best_only = True)","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:38:37.820033Z","iopub.execute_input":"2023-07-25T23:38:37.820699Z","iopub.status.idle":"2023-07-25T23:38:37.825656Z","shell.execute_reply.started":"2023-07-25T23:38:37.820665Z","shell.execute_reply":"2023-07-25T23:38:37.824572Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ジェネレータを用いたモデル学習","metadata":{}},{"cell_type":"code","source":"history = model.fit_generator(train_generator, epochs=epoch, validation_data = test_generator, callbacks = [mc_cb])\n\nmodel.save('finetuning.h5')","metadata":{"execution":{"iopub.status.busy":"2023-07-25T23:38:57.123922Z","iopub.execute_input":"2023-07-25T23:38:57.124607Z","iopub.status.idle":"2023-07-26T00:38:24.186528Z","shell.execute_reply.started":"2023-07-25T23:38:57.124570Z","shell.execute_reply":"2023-07-26T00:38:24.185513Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 予想誤差のグラフ化","metadata":{}},{"cell_type":"code","source":"plt.plot(range(len(history.history['loss'])), history.history['loss'], marker='o', color = 'black', label='loss')\nplt.plot(range(len(history.history['val_loss'])), history.history['val_loss'], marker='v', linestyle='--', color='red', label='val_loss')\nplt.xlabel('epoch')\nplt.ylabel('loss')\nplt.legend(loc='best')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-26T00:38:37.487191Z","iopub.execute_input":"2023-07-26T00:38:37.487547Z","iopub.status.idle":"2023-07-26T00:38:37.780254Z","shell.execute_reply.started":"2023-07-26T00:38:37.487516Z","shell.execute_reply":"2023-07-26T00:38:37.778983Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 予想精度のグラフ化","metadata":{}},{"cell_type":"code","source":"plt.plot(range(len(history.history['accuracy'])), history.history['accuracy'], marker='o', color = 'black', label='acc')\nplt.plot(range(len(history.history['val_accuracy'])), history.history['val_accuracy'], marker='v', linestyle='--', color = 'red', label='val_acc')\nplt.xlabel('epoch')\nplt.ylabel('accuracy')\nplt.legend(loc='best')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-26T00:38:44.494692Z","iopub.execute_input":"2023-07-26T00:38:44.495075Z","iopub.status.idle":"2023-07-26T00:38:44.772974Z","shell.execute_reply.started":"2023-07-26T00:38:44.495026Z","shell.execute_reply":"2023-07-26T00:38:44.771957Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 分類予測に必要なライブラリをインポート","metadata":{}},{"cell_type":"code","source":"import sys\nimport glob\nimport numpy as np\nfrom keras.preprocessing import image\nfrom keras.models import load_model","metadata":{"execution":{"iopub.status.busy":"2023-07-26T00:40:25.783812Z","iopub.execute_input":"2023-07-26T00:40:25.784216Z","iopub.status.idle":"2023-07-26T00:40:25.789517Z","shell.execute_reply.started":"2023-07-26T00:40:25.784186Z","shell.execute_reply":"2023-07-26T00:40:25.788452Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 画像サイズの設定","metadata":{}},{"cell_type":"code","source":"img_height, img_width = 150, 150","metadata":{"execution":{"iopub.status.busy":"2023-07-26T00:40:53.742824Z","iopub.execute_input":"2023-07-26T00:40:53.743214Z","iopub.status.idle":"2023-07-26T00:40:53.747684Z","shell.execute_reply.started":"2023-07-26T00:40:53.743183Z","shell.execute_reply":"2023-07-26T00:40:53.746741Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 分類クラス名の設定","metadata":{}},{"cell_type":"code","source":"classes = ['dog','cat']\nnb_classes = len(classes)","metadata":{"execution":{"iopub.status.busy":"2023-07-26T00:41:21.792206Z","iopub.execute_input":"2023-07-26T00:41:21.792575Z","iopub.status.idle":"2023-07-26T00:41:21.797425Z","shell.execute_reply.started":"2023-07-26T00:41:21.792546Z","shell.execute_reply":"2023-07-26T00:41:21.796324Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ファインチューニングしたCNNモデルのロード","metadata":{}},{"cell_type":"code","source":"model = load_model('finetuning.h5')","metadata":{"execution":{"iopub.status.busy":"2023-07-26T00:41:46.730226Z","iopub.execute_input":"2023-07-26T00:41:46.730729Z","iopub.status.idle":"2023-07-26T00:41:47.301267Z","shell.execute_reply.started":"2023-07-26T00:41:46.730697Z","shell.execute_reply":"2023-07-26T00:41:47.300109Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# テストフォルダー内の全画像ファイル名を取得","metadata":{}},{"cell_type":"code","source":"filename = glob.glob('/content/drive/MyDrive/data/test/*/*.jpg')","metadata":{"execution":{"iopub.status.busy":"2023-07-26T00:42:23.779110Z","iopub.execute_input":"2023-07-26T00:42:23.779497Z","iopub.status.idle":"2023-07-26T00:42:23.785511Z","shell.execute_reply.started":"2023-07-26T00:42:23.779467Z","shell.execute_reply":"2023-07-26T00:42:23.783996Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# テストフォルダ内の全画像を分類予測し各クラスの分類確率値を出力","metadata":{}},{"cell_type":"code","source":"for i in range(len(filename)):\n print('input:', filename[i])\n\n# 入力画像のロード、4次元テンソルへ変換 \n img = image.load_img(filename[i], target_size = (img_height, img_width))\n x = image.img_to_array(img)\n x = np.expand_dims(x, axis = 0)\n\n# 入力データへの正規化\n x = x / 255.0\n\n# 分類クラスを予測\n pred = model.predict(x)[0]\n\n#予測結果を予測確率が上位10件分、クラス名と予測確率を出力\n top_n = 10\n top_indices = pred.argsort()[-top_n:][::-1]\n result = [(classes[i], pred[i]) for i in top_indices]\n for x in result:\n  print(x)","metadata":{"execution":{"iopub.status.busy":"2023-07-26T00:43:00.396846Z","iopub.execute_input":"2023-07-26T00:43:00.397227Z","iopub.status.idle":"2023-07-26T00:43:00.405329Z","shell.execute_reply.started":"2023-07-26T00:43:00.397196Z","shell.execute_reply":"2023-07-26T00:43:00.404102Z"},"trusted":true},"execution_count":null,"outputs":[]}]}