Желілердің негізгі түсінігі 9
жүктеу/скачать 0.55 Mb.
|
- Бұл бет үшін навигация:
- Б қосымшасының жалғасы
Б қосымшасының жалғасыfaces = np.asarray(faces) faces = np.expand_dims(faces) emotions = pd.get_dummies(data['emotion']).as_matrix() return faces, emotions def preprocess_input(x, v2=True): x = x.astype('float32') x = x / 255 if v2: x = x - 0.5 x = x * 2 return x data_generator = ImageDataGenerator( featurewise_center=False, featurewise_std_normalization=False, rotation_range=10, width_shift_range=0.1, height_shift_range=0.1, zoom_range=.1, horizontal_flip=True) model = mini_XCEPTION(input_shape, num_classes) regularization = l2(l2_regularization) img_input = Input(input_shape) x = Conv2D(8, (3, 3), strides=(1, 1), kernel_regularizer=regularization, use_bias=False)(img_input) x = BatchNormalization()(x) x = Activation('relu')(x) x = Conv2D(8, (3, 3), strides=(1, 1), kernel_regularizer=regularization, use_bias=False)(x) x = BatchNormalization()(x) x = Activation('relu')(x) residual = Conv2D(16, (1, 1), strides = (2, 2), padding = 'same', use_bias = False)(x) residual = BatchNormalization()(residual) x = SeparableConv2D(16, (3, 3), padding='same', kernel_regularizer = regularization, use_bias = False)(x) x = BatchNormalization()(x) x = Activation('relu')(x) x = SeparableConv2D(16, (3, 3), padding='same', kernel_regularizer = regularization, use_bias = False)(x) x = BatchNormalization()(x) Б қосымшасының жалғасыx = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x) x = layers.add([x, residual]) residual = Conv2D(32, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = BatchNormalization()(residual) x = SeparableConv2D(32, (3, 3), padding='same', kernel_regularizer = regularization, use_bias = False)(x) x = BatchNormalization()(x) x = Activation('relu')(x) x = SeparableConv2D(32, (3, 3), padding='same', kernel_regularizer = regularization, use_bias = False)(x) x = BatchNormalization()(x) x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x) x = layers.add([x, residual]) residual = Conv2D(64, (1, 1), strides=(2, 2),padding='same', use_bias=False)(x) residual = BatchNormalization()(residual) x = SeparableConv2D(64, (3, 3), padding = 'same', kernel_regularizer = regularization,use_bias = False)(x) x = BatchNormalization()(x) x = Activation('relu')(x) x = SeparableConv2D(64, (3, 3), padding='same', kernel_regularizer = regularization,use_bias = False)(x) x = BatchNormalization()(x) x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x) x = layers.add([x, residual]) residual = Conv2D(128, (1, 1), strides=(2, 2), padding='same', use_bias = False)(x) residual = BatchNormalization()(residual) x = SeparableConv2D(128, (3, 3), padding='same', kernel_regularizer = regularization, use_bias = False)(x) x = BatchNormalization()(x) x = Activation('relu')(x) x = SeparableConv2D(128, (3, 3), padding='same', kernel_regularizer = regularization, use_bias = False)(x) x = BatchNormalization()(x) x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x) x = layers.add([x, residual]) x = Conv2D(num_classes, (3, 3), padding='same')(x) x = GlobalAveragePooling2D()(x) output = Activation('softmax',name='predictions')(x) model = Model(img_input, output) жүктеу/скачать 0.55 Mb. Достарыңызбен бөлісу:
|