base.py 文件源码

def conv2d(self, filter_size, output_channels, stride=1, padding='SAME', bn=True, activation_fn=tf.nn.relu,
               b_value=0.0, s_value=1.0, trainable=True):
        """
        2D Convolutional Layer.
        :param filter_size: int. assumes square filter
        :param output_channels: int
        :param stride: int
        :param padding: 'VALID' or 'SAME'
        :param activation_fn: tf.nn function
        :param b_value: float
        :param s_value: float
        """
        self.count['conv'] += 1
        scope = 'conv_' + str(self.count['conv'])
        with tf.variable_scope(scope):

            # Conv function
            input_channels = self.input.get_shape()[3]
            if filter_size == 0:  # outputs a 1x1 feature map; used for FCN
                filter_size = self.input.get_shape()[2]
                padding = 'VALID'
            output_shape = [filter_size, filter_size, input_channels, output_channels]
            w = self.weight_variable(name='weights', shape=output_shape, trainable=trainable)
            self.input = tf.nn.conv2d(self.input, w, strides=[1, stride, stride, 1], padding=padding)

            if bn is True:  # batch normalization
                self.input = self.batch_norm(self.input)
            if b_value is not None:  # bias value
                b = self.const_variable(name='bias', shape=[output_channels], value=b_value, trainable=trainable)
                self.input = tf.add(self.input, b)
            if s_value is not None:  # scale value
                s = self.const_variable(name='scale', shape=[output_channels], value=s_value, trainable=trainable)
                self.input = tf.multiply(self.input, s)
            if activation_fn is not None:  # activation function
                self.input = activation_fn(self.input)
        print(scope + ' output: ' + str(self.input.get_shape()))