def create_layer(self, input):
# print('convd2: input_shape: {}'.format(utils.get_incoming_shape(input)))
self.input_shape = utils.get_incoming_shape(input)
number_of_input_channels = self.input_shape[3]
with tf.variable_scope('conv', reuse=False):
# set the W.shape[1] to 1
if isinstance(self.initializer, tf.Tensor):
W = tf.get_variable('W{}'.format(self.name[-2:]),
initializer = self.initializer
)
else:
W = tf.get_variable('W{}'.format(self.name[-2:]),
shape=(self.kernel_size, 1, number_of_input_channels, self.output_channels),
initializer = self.initializer)
b = tf.Variable(tf.zeros([self.output_channels]))
self.encoder_matrix = W
Conv2d.layer_index += 1
output = tf.nn.conv2d(input, W, strides=self.strides, padding='SAME')
# print('convd2: output_shape: {}'.format(utils.get_incoming_shape(output)))
#output = lrelu(tf.add(tf.contrib.layers.batch_norm(output, activation_fn=tf.nn.relu, is_training=True, reuse=None), b))
output = lrelu(tf.add(utils.batch_norm_layer(output, self.is_training,'BN{}'.format(self.name[-2:])), b))
#output = lrelu(tf.add(tf.contrib.layers.batch_norm(output, decay=0.999, center=True, scale=True, updates_collections=None,is_training=True, reuse=None), b))
return output
def conv_2d_layer(incoming,
nb_filter,
filter_size,
strides,
kernel_init,
is_training,
bn=True,
padding='same',
activation=None,
bias='True',
bias_init=None,
scope=None):
"""
构建二维卷积层函数
:param incoming: 输入
:param nb_filter: 卷积核（feature map）个数
:param filter_size: 卷积核大小
:param strides: 步长
:param kernel_init: 卷积核参数初始化方法
:param is_training: 是否是训练
:param bn: 是否需要batch normalization
:param padding: padding方法
:param activation: 激活函数
:param bias: 是否需要偏移量
:param bias_init: 偏移量初始化方法
:param scope:
:return: 返回经过卷积的输出
"""
input_shape = get_incoming_shape(incoming)
# 输入必须为4维矩阵
assert len(input_shape) == 4
with tf.variable_scope(scope):
con2d_output = tf.layers.conv2d(incoming,
filters=nb_filter,
kernel_size=filter_size,
strides=strides,
padding=padding,
activation=activation,
kernel_initializer=kernel_init,
use_bias=bias,
bias_initializer=bias_init)
if bn:
return tf.layers.batch_normalization(con2d_output,
axis=-1,
training=is_training)
else:
return con2d_output
def create_layer(self, input, is_training=True):
self.input_shape = utils.get_incoming_shape(input)
number_of_input_channels = self.input_shape[3]
with tf.variable_scope('conv', reuse=False):
W = tf.get_variable('W{}'.format(self.name),
shape=(self.kernel_size, self.kernel_size, number_of_input_channels, self.output_channels))
b = tf.Variable(tf.zeros([self.output_channels]))
self.encoder_matrix = W
Conv2d.layer_index += 1
output = tf.nn.conv2d(input, W, strides=self.strides, padding='SAME')
#output = lrelu(tf.add(tf.contrib.layers.batch_norm(output, scope="norm{}".format(self.name), is_training=is_training), b))
output = lrelu(tf.add(output, b))
return output
def create_layer(self, input):
# print('convd2: input_shape: {}'.format(utils.get_incoming_shape(input)))
self.input_shape = utils.get_incoming_shape(input)
number_of_input_channels = self.input_shape[3]
with tf.variable_scope('conv', reuse=False):
W = tf.get_variable('W{}'.format(self.name[-3:]),
shape=(self.kernel_size, self.kernel_size, number_of_input_channels, self.output_channels))
b = tf.Variable(tf.zeros([self.output_channels]))
self.encoder_matrix = W
Conv2d.layer_index += 1
output = tf.nn.conv2d(input, W, strides=self.strides, padding='SAME')
# print('convd2: output_shape: {}'.format(utils.get_incoming_shape(output)))
output = lrelu(tf.add(tf.contrib.layers.batch_norm(output), b))
return output
def create_layer(self, input):
# print('convd2: input_shape: {}'.format(utils.get_incoming_shape(input)))
self.input_shape = utils.get_incoming_shape(input)
number_of_input_channels = self.input_shape[3]
with tf.variable_scope('conv', reuse=None):
W = tf.get_variable('W{}'.format(self.name[-3:]),
shape=(self.kernel_size, self.kernel_size,
number_of_input_channels,
self.output_channels))
b = tf.Variable(tf.zeros([self.output_channels]))
self.encoder_matrix = W
Conv2d.layer_index += 1
output = tf.nn.conv2d(input, W, strides=self.strides, padding='SAME')
# print('convd2: output_shape: {}'.format(utils.get_incoming_shape(output)))
output = lrelu(tf.add(tf.contrib.layers.batch_norm(output), b))
return output