def one_block_model(self, input_tensor):
"""
Method to model one cnn. It doesn't compile the model.
:param input_tensor: tensor, to feed the two path
:return: output: tensor, the output of the cnn
"""
# localPath
loc_path = Conv2D(64, (7, 7), data_format='channels_first', padding='valid', activation='relu', use_bias=True,
kernel_regularizer=regularizers.l1_l2(self.l1_rate, self.l2_rate),
kernel_constraint=max_norm(2.),
bias_constraint=max_norm(2.), kernel_initializer='lecun_uniform', bias_initializer='zeros')(input_tensor)
loc_path = MaxPooling2D(pool_size=(4, 4), data_format='channels_first', strides=1, padding='valid')(loc_path)
loc_path = Dropout(self.dropout_rate)(loc_path)
loc_path = Conv2D(64, (3, 3), data_format='channels_first', padding='valid', activation='relu', use_bias=True,
kernel_initializer='lecun_uniform', bias_initializer='zeros',
kernel_regularizer=regularizers.l1_l2(self.l1_rate, self.l2_rate),kernel_constraint=max_norm(2.),
bias_constraint=max_norm(2.))(loc_path)
loc_path = MaxPooling2D(pool_size=(2, 2), data_format='channels_first', strides=1, padding='valid')(loc_path)
loc_path = Dropout(self.dropout_rate)(loc_path)
# globalPath
glob_path = Conv2D(160, (13, 13), data_format='channels_first', strides=1, padding='valid', activation='relu', use_bias=True,
kernel_initializer='lecun_uniform', bias_initializer='zeros',
kernel_regularizer=regularizers.l1_l2(self.l1_rate, self.l2_rate),
kernel_constraint=max_norm(2.),
bias_constraint=max_norm(2.))(input_tensor)
glob_path = Dropout(self.dropout_rate)(glob_path)
# concatenation of the two path
path = Concatenate(axis=1)([loc_path, glob_path])
# output layer
output = Conv2D(5, (21, 21), data_format='channels_first', strides=1, padding='valid', activation='softmax', use_bias=True,
kernel_initializer='lecun_uniform', bias_initializer='zeros')(path)
return output
评论列表
文章目录
