{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\n# наборы данных для экспериментов\nfrom tensorflow.keras.datasets import cifar10\n# последовательная модель (стек слоев)\nfrom tensorflow.keras.models import Sequential, Model\n# полносвязный слой и слой выпрямляющий матрицу в вектор\nfrom tensorflow.keras.layers import Dense, Flatten, Input\n# слой выключения нейронов и слой нормализации выходных данных (нормализует данные в пределах текущей выборки)\nfrom tensorflow.keras.layers import Dropout, BatchNormalization, SpatialDropout2D, GaussianDropout\n# слои свертки и подвыборки\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, AveragePooling2D\n# работа с обратной связью от обучающейся нейронной сети\nfrom tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau\n# вспомогательные инструменты\nfrom tensorflow.keras import utils\nfrom tensorflow.keras.regularizers import *\n\nimport os\nfrom tensorflow.random import set_seed\ndef seed_everything(seed):\n    np.random.seed(seed)\n    set_seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    os.environ['TF_DETERMINISTIC_OPS'] = '1'\n\nseed = 42\nseed_everything(seed)\n\n# работа с изображениями\nfrom tensorflow.keras.preprocessing import image\nimport matplotlib.pyplot as plt\n%matplotlib inline ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Размер мини-выборки\nbatch_size = 64\n# Количество классов изображений\nnb_classes = 10\n# Количество эпох для обучения\nnb_epoch = 40\n# Размер изображений\nimg_rows, img_cols = 32, 32\n# Количество каналов в изображении: RGB\nimg_channels = 3","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Загрузка данных"},{"metadata":{"trusted":true},"cell_type":"code","source":"(X_train, y_train), (X_test, y_test) = cifar10.load_data()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Нормализация данных"},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.reshape((50000, img_cols, img_rows, img_channels))\nX_train = X_train.astype('float32')\nX_test = X_test.reshape((10000, img_cols, img_rows, img_channels))\nX_test = X_test.astype('float32')\nX_train /= 255\nX_test /= 255","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Преобразование в One Hot Encoding"},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train = utils.to_categorical(y_train, nb_classes)\nY_test = utils.to_categorical(y_test, nb_classes)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Инициализация модели нейросети"},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras import layers, Model\ndef conv2D_block(x, num_conv=2, num_filters=32, drop_rate=0.25):\n    for _ in range(num_conv):\n        x = Conv2D(num_filters, (3, 3), activation='relu', padding='same')(x)\n    x = MaxPooling2D(pool_size=(2, 2))(x)\n    x = BatchNormalization()(x)\n    x = Dropout(drop_rate)(x)\n    return x\n\ndef conv2D_net(x, nb_classes, num_block=3, num_conv_strategy=[1,2,2],\n               num_filters_st=[32, 64, 128], drop_rates=[0.25, 0.25, 0.25]):\n    x = Conv2D(16, (3, 3), activation='relu', \n               padding='same',input_shape=(img_rows, img_cols, img_channels))(x)\n    for i in range(num_block):\n        x = conv2D_block(x, num_conv_strategy[i], num_filters_st[i], drop_rates[i])\n    x = Flatten()(x)\n    x = Dense(512, activation='relu')(x)\n    x = BatchNormalization()(x)\n    x = Dropout(0.75)(x)\n    x = Dense(nb_classes, activation='softmax')(x)\n    return x\n\ninput_layer = Input(shape=(img_rows, img_cols, img_channels), name='input_layer')\noutput_layer = conv2D_net(input_layer, nb_classes)\nmodel = Model(input_layer, output_layer)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Сведения об инициализированной модели"},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Компиляция модели"},{"metadata":{"trusted":true},"cell_type":"code","source":"callbacks_list = [EarlyStopping(monitor='val_loss', patience=5),\n                  ModelCheckpoint(filepath='my_model.h5',\n                                  monitor='val_loss',\n                                  save_best_only=True),\n                  ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=3)\n                  ] \nmodel.compile(loss='categorical_crossentropy',\n              optimizer='nadam',\n              metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Обучение"},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nhistory = model.fit(X_train, Y_train,\n              batch_size=batch_size,\n              epochs=nb_epoch,\n              callbacks=callbacks_list,\n              validation_split=0.1,\n              verbose=1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Оценка качества обучения"},{"metadata":{"trusted":true},"cell_type":"code","source":"scores = model.evaluate(X_test, Y_test, verbose=1)\nprint(\"Доля верных ответов на тестовых данных, в процентах:\", round(scores[1] * 100, 4))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['accuracy'], \n         label='Доля правильных ответов на обучающем наборе')\nplt.plot(history.history['val_accuracy'], \n         label='Доля правильных ответов на проверочном наборе')\nplt.xlabel('Эпоха обучения')\nplt.ylabel('Доля правильных ответов')\nplt.legend()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['loss'], \n         label='Оценка потерь на обучающем наборе')\nplt.plot(history.history['val_loss'], \n         label='Оценка потерь на проверочном наборе')\nplt.xlabel('Эпоха обучения')\nplt.ylabel('Оценка потерь')\nplt.legend()\nplt.show()","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}