def model_generator(): nch = 256 g_input = Input(shape=[100]) H = Dense(nch * 14 * 14, init='glorot_normal')(g_input) H = BatchNormalization(mode=2)(H) H = Activation('relu')(H) H = dim_ordering_reshape(nch, 14)(H) H = UpSampling2D(size=(2, 2))(H) H = Convolution2D(int(nch / 2), 3, 3, border_mode='same', init='glorot_uniform')(H) H = BatchNormalization(mode=2, axis=1)(H) H = Activation('relu')(H) H = Convolution2D(int(nch / 4), 3, 3, border_mode='same', init='glorot_uniform')(H) H = BatchNormalization(mode=2, axis=1)(H) H = Activation('relu')(H) H = Convolution2D(1, 1, 1, border_mode='same', init='glorot_uniform')(H) g_V = Activation('sigmoid')(H) return Model(g_input, g_V)
def model_generator(): ch_num = 256 g_input = Input(shape=[100]) H = Dense(ch_num * 14 * 14)(g_input) H = BatchNormalization()(H) H = Activation('relu')(H) H = dim_ordering_reshape(ch_num, 14)(H) H = UpSampling2D(size=(2, 2))(H) H = Conv2D(int(ch_num / 2), (3, 3), padding='same')(H) H = BatchNormalization()(H) H = Activation('relu')(H) H = Conv2D(int(ch_num / 4), (3, 3), padding='same')(H) H = BatchNormalization()(H) H = Activation('relu')(H) H = Conv2D(1, (1, 1), padding='same')(H) g_V = Activation('sigmoid')(H) return Model(g_input, g_V)
def model_generator(): nch = 128 g_input = Input(shape=[400]) H = Dense(nch * 46 * 46)(g_input) H = BatchNormalization(mode=2)(H) H = Activation('relu')(H) H = dim_ordering_reshape(nch, 46)(H) H = UpSampling2D(size=(2, 2))(H) H = Convolution2D(int(nch / 2), 3, 3, border_mode='same')(H) H = BatchNormalization(mode=2, axis=1)(H) H = Activation('relu')(H) H = Convolution2D(int(nch / 4), 3, 3, border_mode='same')(H) H = BatchNormalization(mode=2, axis=1)(H) H = Activation('relu')(H) H = Convolution2D(1, 1, 1, border_mode='same')(H) g_V = Activation('sigmoid')(H) return Model(g_input, g_V)
def model_generator(): nch = 256 g_input = Input(shape=[100]) H = Dense(nch * 14 * 14)(g_input) H = BatchNormalization()(H) H = Activation("relu")(H) H = dim_ordering_reshape(nch, 14)(H) H = UpSampling2D(size=(2, 2))(H) H = Conv2D(int(nch / 2), (3, 3), padding="same")(H) H = BatchNormalization()(H) H = Activation("relu")(H) H = Conv2D(int(nch / 4), (3, 3), padding="same")(H) H = BatchNormalization()(H) H = Activation("relu")(H) H = Conv2D(1, (1, 1), padding="same")(H) g_V = Activation("sigmoid")(H) return Model(g_input, g_V)
def model_generator(): nch = 256 g_input = Input(shape=[100]) H = Dense(nch * 14 * 14)(g_input) H = BatchNormalization(mode=2)(H) H = Activation('relu')(H) H = dim_ordering_reshape(nch, 14)(H) H = UpSampling2D(size=(2, 2))(H) H = Convolution2D(int(nch / 2), 3, 3, border_mode='same')(H) H = BatchNormalization(mode=2, axis=1)(H) H = Activation('relu')(H) H = Convolution2D(int(nch / 4), 3, 3, border_mode='same')(H) H = BatchNormalization(mode=2, axis=1)(H) H = Activation('relu')(H) H = Convolution2D(1, 1, 1, border_mode='same')(H) g_V = Activation('sigmoid')(H) return Model(g_input, g_V)
def generator(): c = 256 g_input = Input(shape=[100]) H = Dense(c * 14 * 14, kernel_initializer='glorot_normal')(g_input) H = BatchNormalization()(H) H = Activation('relu')(H) H = dim_ordering_reshape(c, 14)(H) H = UpSampling2D(size=(2, 2))(H) H = Convolution2D(int(c / 2), kernel_size=3, strides=3, padding='same', init='glorot_uniform')(H) H = BatchNormalization(axis=1)(H) H = Activation('relu')(H) H = Convolution2D(1, kernel_size=1, strides=1, padding='same', init='glorot_uniform')(H) g_V = Activation('sigmoid')(H) return Model(g_input, g_V)
def model_generator(): nch = 256 g_input = Input(shape=[100]) H = Dense(256 * 14 * 14, init='glorot_normal')(g_input) H = BatchNormalization()(H) H = Activation('relu')(H) H = dim_ordering_reshape(256, 14) H = UpSampling2D(size=(2, 2))(H) H = Conv2D(128, 3, 3, border_mode='same', init='glorot_normal')(H) H = BatchNormalization(axis=1)(H) H = Activation('relu')(H) H = Conv2D(64, 3, 3, border_mode='same', init='glorot_normal')(H) H = BatchNormalization(axis=1)(H) H = Activation('relu')(H) H = Conv2D(1, 1, 1, border_mode='same', init='glorot_normal')(H) g_V = Activation('sigmoid')(H) return Model(g_input, g_V)