{"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":"2023-07-28T02:45:06.517637Z","iopub.execute_input":"2023-07-28T02:45:06.518155Z","iopub.status.idle":"2023-07-28T02:45:06.537321Z","shell.execute_reply.started":"2023-07-28T02:45:06.518092Z","shell.execute_reply":"2023-07-28T02:45:06.536028Z"},"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":"2023-07-28T02:45:06.540046Z","iopub.execute_input":"2023-07-28T02:45:06.540404Z","iopub.status.idle":"2023-07-28T02:45:15.587384Z","shell.execute_reply.started":"2023-07-28T02:45:06.540372Z","shell.execute_reply":"2023-07-28T02:45:15.586332Z"},"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":"2023-07-28T02:45:15.588869Z","iopub.execute_input":"2023-07-28T02:45:15.589674Z","iopub.status.idle":"2023-07-28T02:45:31.919916Z","shell.execute_reply.started":"2023-07-28T02:45:15.589620Z","shell.execute_reply":"2023-07-28T02:45:31.918858Z"},"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":"2023-07-28T02:45:31.921590Z","iopub.execute_input":"2023-07-28T02:45:31.922132Z","iopub.status.idle":"2023-07-28T02:45:31.929536Z","shell.execute_reply.started":"2023-07-28T02:45:31.922088Z","shell.execute_reply":"2023-07-28T02:45:31.928479Z"},"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":"2023-07-28T02:45:31.933920Z","iopub.execute_input":"2023-07-28T02:45:31.934440Z","iopub.status.idle":"2023-07-28T02:45:31.940636Z","shell.execute_reply.started":"2023-07-28T02:45:31.934400Z","shell.execute_reply":"2023-07-28T02:45:31.939624Z"},"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":"2023-07-28T02:45:31.942203Z","iopub.execute_input":"2023-07-28T02:45:31.942653Z","iopub.status.idle":"2023-07-28T02:45:31.951871Z","shell.execute_reply.started":"2023-07-28T02:45:31.942618Z","shell.execute_reply":"2023-07-28T02:45:31.950894Z"},"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":"2023-07-28T02:45:31.955499Z","iopub.execute_input":"2023-07-28T02:45:31.955899Z","iopub.status.idle":"2023-07-28T02:45:38.625265Z","shell.execute_reply.started":"2023-07-28T02:45:31.955875Z","shell.execute_reply":"2023-07-28T02:45:38.624127Z"},"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":"2023-07-28T02:45:38.626614Z","iopub.execute_input":"2023-07-28T02:45:38.627001Z","iopub.status.idle":"2023-07-28T02:45:38.754253Z","shell.execute_reply.started":"2023-07-28T02:45:38.626930Z","shell.execute_reply":"2023-07-28T02:45:38.753246Z"},"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":"2023-07-28T02:45:38.755640Z","iopub.execute_input":"2023-07-28T02:45:38.756012Z","iopub.status.idle":"2023-07-28T02:45:38.762038Z","shell.execute_reply.started":"2023-07-28T02:45:38.755950Z","shell.execute_reply":"2023-07-28T02:45:38.760871Z"},"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":"2023-07-28T02:45:38.763521Z","iopub.execute_input":"2023-07-28T02:45:38.764124Z","iopub.status.idle":"2023-07-28T02:45:38.791188Z","shell.execute_reply.started":"2023-07-28T02:45:38.764087Z","shell.execute_reply":"2023-07-28T02:45:38.790431Z"},"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","metadata":{}},{"cell_type":"code","source":"model.compile(loss = 'categorical_crossentropy', optimizer = 'sgd', metrics = ['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2023-07-28T02:45:38.792385Z","iopub.execute_input":"2023-07-28T02:45:38.792717Z","iopub.status.idle":"2023-07-28T02:45:38.819000Z","shell.execute_reply.started":"2023-07-28T02:45:38.792686Z","shell.execute_reply":"2023-07-28T02:45:38.818135Z"},"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)","metadata":{"execution":{"iopub.status.busy":"2023-07-28T02:45:38.820407Z","iopub.execute_input":"2023-07-28T02:45:38.820782Z","iopub.status.idle":"2023-07-28T02:45:38.826602Z","shell.execute_reply.started":"2023-07-28T02:45:38.820751Z","shell.execute_reply":"2023-07-28T02:45:38.825661Z"},"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":"2023-07-28T02:45:38.828062Z","iopub.execute_input":"2023-07-28T02:45:38.829011Z","iopub.status.idle":"2023-07-28T02:45:39.689643Z","shell.execute_reply.started":"2023-07-28T02:45:38.828952Z","shell.execute_reply":"2023-07-28T02:45:39.688636Z"},"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":"2023-07-28T02:45:39.694475Z","iopub.execute_input":"2023-07-28T02:45:39.694775Z","iopub.status.idle":"2023-07-28T02:45:39.699620Z","shell.execute_reply.started":"2023-07-28T02:45:39.694748Z","shell.execute_reply":"2023-07-28T02:45:39.698634Z"},"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":"2023-07-28T02:45:39.701191Z","iopub.execute_input":"2023-07-28T02:45:39.701857Z","iopub.status.idle":"2023-07-28T02:45:39.710831Z","shell.execute_reply.started":"2023-07-28T02:45:39.701824Z","shell.execute_reply":"2023-07-28T02:45:39.709730Z"},"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":"2023-07-28T02:45:39.712441Z","iopub.execute_input":"2023-07-28T02:45:39.712790Z","iopub.status.idle":"2023-07-28T02:45:40.326527Z","shell.execute_reply.started":"2023-07-28T02:45:39.712758Z","shell.execute_reply":"2023-07-28T02:45:40.325561Z"},"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":"2023-07-28T02:45:40.327934Z","iopub.execute_input":"2023-07-28T02:45:40.328522Z","iopub.status.idle":"2023-07-28T02:45:40.542656Z","shell.execute_reply.started":"2023-07-28T02:45:40.328488Z","shell.execute_reply":"2023-07-28T02:45:40.541639Z"},"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":"2023-07-28T02:45:40.544228Z","iopub.execute_input":"2023-07-28T02:45:40.544578Z","iopub.status.idle":"2023-07-28T02:45:40.550188Z","shell.execute_reply.started":"2023-07-28T02:45:40.544543Z","shell.execute_reply":"2023-07-28T02:45:40.549031Z"},"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":"2023-07-28T02:45:40.551883Z","iopub.execute_input":"2023-07-28T02:45:40.552657Z","iopub.status.idle":"2023-07-28T03:45:18.163305Z","shell.execute_reply.started":"2023-07-28T02:45:40.552625Z","shell.execute_reply":"2023-07-28T03:45:18.162165Z"},"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":"2023-07-28T03:45:18.164674Z","iopub.execute_input":"2023-07-28T03:45:18.165071Z","iopub.status.idle":"2023-07-28T03:45:18.454833Z","shell.execute_reply.started":"2023-07-28T03:45:18.165032Z","shell.execute_reply":"2023-07-28T03:45:18.453897Z"},"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":"2023-07-28T03:45:18.456370Z","iopub.execute_input":"2023-07-28T03:45:18.456718Z","iopub.status.idle":"2023-07-28T03:45:18.734837Z","shell.execute_reply.started":"2023-07-28T03:45:18.456685Z","shell.execute_reply":"2023-07-28T03:45:18.733896Z"},"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":"2023-07-28T03:45:18.736414Z","iopub.execute_input":"2023-07-28T03:45:18.737007Z","iopub.status.idle":"2023-07-28T03:45:18.742746Z","shell.execute_reply.started":"2023-07-28T03:45:18.736947Z","shell.execute_reply":"2023-07-28T03:45:18.741487Z"},"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":"2023-07-28T03:45:18.744459Z","iopub.execute_input":"2023-07-28T03:45:18.744803Z","iopub.status.idle":"2023-07-28T03:45:18.754111Z","shell.execute_reply.started":"2023-07-28T03:45:18.744772Z","shell.execute_reply":"2023-07-28T03:45:18.753138Z"},"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":"2023-07-28T03:45:18.757070Z","iopub.execute_input":"2023-07-28T03:45:18.757357Z","iopub.status.idle":"2023-07-28T03:45:18.764993Z","shell.execute_reply.started":"2023-07-28T03:45:18.757314Z","shell.execute_reply":"2023-07-28T03:45:18.764131Z"},"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":"2023-07-28T03:45:18.766394Z","iopub.execute_input":"2023-07-28T03:45:18.766832Z","iopub.status.idle":"2023-07-28T03:45:19.197727Z","shell.execute_reply.started":"2023-07-28T03:45:18.766795Z","shell.execute_reply":"2023-07-28T03:45:19.196687Z"},"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":"2023-07-28T03:45:19.199043Z","iopub.execute_input":"2023-07-28T03:45:19.199377Z","iopub.status.idle":"2023-07-28T03:45:19.205907Z","shell.execute_reply.started":"2023-07-28T03:45:19.199347Z","shell.execute_reply":"2023-07-28T03:45:19.204940Z"},"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":"2023-07-28T03:45:19.207337Z","iopub.execute_input":"2023-07-28T03:45:19.207910Z","iopub.status.idle":"2023-07-28T03:45:19.216345Z","shell.execute_reply.started":"2023-07-28T03:45:19.207875Z","shell.execute_reply":"2023-07-28T03:45:19.215468Z"},"trusted":true},"execution_count":null,"outputs":[]}]}