{"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":"2023-07-29T20:56:23.225948Z","iopub.execute_input":"2023-07-29T20:56:23.226435Z","iopub.status.idle":"2023-07-29T20:56:23.234346Z","shell.execute_reply.started":"2023-07-29T20:56:23.226397Z","shell.execute_reply":"2023-07-29T20:56:23.233259Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"・データの準備\n\nzipファイルの展開をする\n\n使用するディレクトリを作成する\n\n画像を作成したディレクトリに移動させる","metadata":{}},{"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":"2023-07-29T20:56:23.237269Z","iopub.execute_input":"2023-07-29T20:56:23.237974Z","iopub.status.idle":"2023-07-29T20:56:35.999594Z","shell.execute_reply.started":"2023-07-29T20:56:23.237933Z","shell.execute_reply":"2023-07-29T20:56:35.998774Z"},"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])\n\n","metadata":{"execution":{"iopub.status.busy":"2023-07-29T20:56:36.001409Z","iopub.execute_input":"2023-07-29T20:56:36.001762Z","iopub.status.idle":"2023-07-29T20:56:36.072638Z","shell.execute_reply.started":"2023-07-29T20:56:36.001704Z","shell.execute_reply":"2023-07-29T20:56:36.071618Z"},"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()\n","metadata":{"execution":{"iopub.status.busy":"2023-07-29T20:56:36.074297Z","iopub.execute_input":"2023-07-29T20:56:36.074830Z","iopub.status.idle":"2023-07-29T20:56:36.456508Z","shell.execute_reply.started":"2023-07-29T20:56:36.074789Z","shell.execute_reply":"2023-07-29T20:56:36.455534Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os \n\n# train用フォルダ作成(学習データ)\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(検証データ)\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(テストデータ)\nos.makedirs('/kaggle/working/images/test/test', exist_ok=True)","metadata":{"execution":{"iopub.status.busy":"2023-07-29T20:56:36.459600Z","iopub.execute_input":"2023-07-29T20:56:36.460574Z","iopub.status.idle":"2023-07-29T20:56:36.466582Z","shell.execute_reply.started":"2023-07-29T20:56:36.460538Z","shell.execute_reply":"2023-07-29T20:56:36.465089Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 画像のファイルパスを取得\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":"2023-07-29T20:56:36.468351Z","iopub.execute_input":"2023-07-29T20:56:36.468887Z","iopub.status.idle":"2023-07-29T20:56:36.610725Z","shell.execute_reply.started":"2023-07-29T20:56:36.468849Z","shell.execute_reply":"2023-07-29T20:56:36.609737Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# trainフォルダのファイルを8:2に分割(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":"2023-07-29T20:56:36.611959Z","iopub.execute_input":"2023-07-29T20:56:36.612352Z","iopub.status.idle":"2023-07-29T20:56:36.622408Z","shell.execute_reply.started":"2023-07-29T20:56:36.612315Z","shell.execute_reply":"2023-07-29T20:56:36.618955Z"},"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":"2023-07-29T20:56:36.624011Z","iopub.execute_input":"2023-07-29T20:56:36.624365Z","iopub.status.idle":"2023-07-29T20:56:36.703913Z","shell.execute_reply.started":"2023-07-29T20:56:36.624334Z","shell.execute_reply":"2023-07-29T20:56:36.702091Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"・学習の準備\n\nエポック数とは、全データを学習する回数のことであり、バッチサイズとは1ステップで学習する画像の枚数のことである。\n\n学習では各データを順番に入力してモデルのパラメータを更新し、この学習データを1通り使用した状態が1エポックである。\n\nバッチサイズとは、パラメータの更新時に入力するデータ数である。","metadata":{}},{"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(submissionファイル提出時にスコアが一番優秀だった5を採用)\nepochs = 5\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":"2023-07-29T20:56:36.704778Z","iopub.status.idle":"2023-07-29T20:56:36.705401Z","shell.execute_reply.started":"2023-07-29T20:56:36.705209Z","shell.execute_reply":"2023-07-29T20:56:36.705228Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"・ImageDataGenerator作成\n\n画像読み込みを逐次的に行い、メモリ負荷を軽減するためにKerasライブラリのモジュールであるImageDataGeneratorを使用する\n\n作成前にデータの正規化を実施する","metadata":{}},{"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に変換して正規化\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)\n","metadata":{"execution":{"iopub.status.busy":"2023-07-29T20:56:36.706522Z","iopub.status.idle":"2023-07-29T20:56:36.706963Z","shell.execute_reply.started":"2023-07-29T20:56:36.706785Z","shell.execute_reply":"2023-07-29T20:56:36.706804Z"},"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) # rescaleで各画素のスケールを0～255から0～1に変換して正規化\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":"2023-07-29T20:56:36.708374Z","iopub.status.idle":"2023-07-29T20:56:36.709218Z","shell.execute_reply.started":"2023-07-29T20:56:36.709026Z","shell.execute_reply":"2023-07-29T20:56:36.709047Z"},"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) # rescaleで各画素のスケールを0～255から0～1に変換して正規化\ntest_generator = test_datagen.flow_from_directory(\n    directory=test_data_dir,\n    target_size=(img_width, img_height),\n    class_mode=None,\n    shuffle=False \n)","metadata":{"execution":{"iopub.status.busy":"2023-07-29T20:56:36.710156Z","iopub.status.idle":"2023-07-29T20:56:36.710516Z","shell.execute_reply.started":"2023-07-29T20:56:36.710340Z","shell.execute_reply":"2023-07-29T20:56:36.710358Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"・学習済みモデルをインポート\n\n畳み込みニューラルネットワークの1種である、学習済みモデルのVGG16を読み込み、最終層は差し替えるため読み込まない。","metadata":{}},{"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":"2023-07-29T20:56:36.711393Z","iopub.status.idle":"2023-07-29T20:56:36.711745Z","shell.execute_reply.started":"2023-07-29T20:56:36.711558Z","shell.execute_reply":"2023-07-29T20:56:36.711573Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"・モデルの作成\n\n転移学習を行うため、VGG16のパラメータは凍結させ、最終層に全結合層を追加する。","metadata":{}},{"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":"2023-07-29T20:56:36.713478Z","iopub.status.idle":"2023-07-29T20:56:36.714010Z","shell.execute_reply.started":"2023-07-29T20:56:36.713835Z","shell.execute_reply":"2023-07-29T20:56:36.713854Z"},"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":"2023-07-29T20:56:36.714799Z","iopub.status.idle":"2023-07-29T20:56:36.715571Z","shell.execute_reply.started":"2023-07-29T20:56:36.715382Z","shell.execute_reply":"2023-07-29T20:56:36.715402Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.summary() #構築したモデルの概要を表示","metadata":{"execution":{"iopub.status.busy":"2023-07-29T20:56:36.716780Z","iopub.status.idle":"2023-07-29T20:56:36.717128Z","shell.execute_reply.started":"2023-07-29T20:56:36.716951Z","shell.execute_reply":"2023-07-29T20:56:36.716967Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras import optimizers\n#モデルをコンパイルして学習方法を指定。\n#損失関数にクロスエントロピー・最適化アルゴリズムにAdam・学習中の評価指標にaccuracyを設定\nmodel.compile(loss='categorical_crossentropy',\n              optimizer=optimizers.Adam(learning_rate=1e-3),\n              metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2023-07-29T20:56:36.718170Z","iopub.status.idle":"2023-07-29T20:56:36.718798Z","shell.execute_reply.started":"2023-07-29T20:56:36.718603Z","shell.execute_reply":"2023-07-29T20:56:36.718622Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"・学習の実行\n\nステップ数とは、全データ数/バッチサイズから求められ、1エポック当たり何回パラメータを更新するかを表す数である。","metadata":{}},{"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":"2023-07-29T20:56:36.719806Z","iopub.status.idle":"2023-07-29T20:56:36.720145Z","shell.execute_reply.started":"2023-07-29T20:56:36.719973Z","shell.execute_reply":"2023-07-29T20:56:36.719989Z"},"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":"2023-07-29T20:56:36.721382Z","iopub.status.idle":"2023-07-29T20:56:36.721737Z","shell.execute_reply.started":"2023-07-29T20:56:36.721552Z","shell.execute_reply":"2023-07-29T20:56:36.721569Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"・評価\n\nvalデータを用いてモデルの精度を評価する","metadata":{}},{"cell_type":"code","source":"model.evaluate(validation_generator)","metadata":{"execution":{"iopub.status.busy":"2023-07-29T20:56:36.722621Z","iopub.status.idle":"2023-07-29T20:56:36.722962Z","shell.execute_reply.started":"2023-07-29T20:56:36.722799Z","shell.execute_reply":"2023-07-29T20:56:36.722815Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 訓練したモデルを用いてテストデータの予測を実施\nimport numpy as np\np = model.predict(test_generator)\npred = np.argmax(p, axis=1)\npred","metadata":{"execution":{"iopub.status.busy":"2023-07-29T20:56:36.725590Z","iopub.status.idle":"2023-07-29T20:56:36.726419Z","shell.execute_reply.started":"2023-07-29T20:56:36.726107Z","shell.execute_reply":"2023-07-29T20:56:36.726134Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"・結果を提出できるように修正する","metadata":{}},{"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":"2023-07-29T20:56:36.728066Z","iopub.status.idle":"2023-07-29T20:56:36.728892Z","shell.execute_reply.started":"2023-07-29T20:56:36.728551Z","shell.execute_reply":"2023-07-29T20:56:36.728581Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"・結果の保存\n\nnotebookをRun Allで実行し、生成されたsubmissionファイルを一度ダウンロードして提出することでScore算出が可能になる","metadata":{}},{"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":"2023-07-29T20:56:36.730320Z","iopub.status.idle":"2023-07-29T20:56:36.731341Z","shell.execute_reply.started":"2023-07-29T20:56:36.731028Z","shell.execute_reply":"2023-07-29T20:56:36.731057Z"},"trusted":true},"execution_count":null,"outputs":[]}]}