def atrous_conv2d(name, x, w=None, num_filters=16, kernel_size=(3, 3), padding='SAME', dilation_rate=1,
initializer=tf.contrib.layers.xavier_initializer(), l2_strength=0.0, bias=0.0,
activation=None, batchnorm_enabled=False, max_pool_enabled=False, dropout_keep_prob=-1,
is_training=True):
"""
This block is responsible for a Dilated convolution 2D layer followed by optional (non-linearity, dropout,
max-pooling).
Note that: "is_training" should be passed by a correct value based on being in either training or testing.
:param name: (string) The name scope provided by the upper tf.name_scope('name') as scope.
:param x: (tf.tensor) The input to the layer (N, H, W, C).
:param w:
:param num_filters: (integer) No. of filters (This is the output depth)
:param kernel_size: (integer tuple) The size of the convolving kernel.
:param padding: (string) The amount of padding required.
:param dilation_rate: (integer) The amount of dilation required. If equals 1, it means normal convolution.
:param initializer: (tf.contrib initializer) The initialization scheme, He et al. normal or Xavier normal are
recommended.
:param l2_strength:(weight decay) (float) L2 regularization parameter.
:param bias: (float) Amount of bias.
:param activation: (tf.graph operator) The activation function applied after the convolution operation. If None,
linear is applied.
:param batchnorm_enabled: (boolean) for enabling batch normalization.
:param max_pool_enabled: (boolean) for enabling max-pooling 2x2 to decrease width and height by a factor of 2.
:param dropout_keep_prob: (float) for the probability of keeping neurons. If equals -1, it means no dropout
:param is_training: (boolean) to diff. between training and testing (important for batch normalization and dropout)
:return: The output tensor of the layer (N, H', W', C').
"""
with tf.variable_scope(name) as scope:
conv_o_b = __atrous_conv2d_p(scope, x=x, w=w, num_filters=num_filters, kernel_size=kernel_size,
padding=padding, dilation_rate=dilation_rate,
initializer=initializer, l2_strength=l2_strength, bias=bias)
if batchnorm_enabled:
conv_o_bn = tf.layers.batch_normalization(conv_o_b, training=is_training)
if not activation:
conv_a = conv_o_bn
else:
conv_a = activation(conv_o_bn)
else:
if not activation:
conv_a = conv_o_b
else:
conv_a = activation(conv_o_b)
def dropout_with_keep():
return tf.nn.dropout(conv_a, dropout_keep_prob)
def dropout_no_keep():
return tf.nn.dropout(conv_a, 1.0)
if dropout_keep_prob != -1:
conv_o_dr = tf.cond(is_training, dropout_with_keep, dropout_no_keep)
else:
conv_o_dr = conv_a
conv_o = conv_o_dr
if max_pool_enabled:
conv_o = max_pool_2d(conv_o_dr)
return conv_o
def conv2d(name,
x,
w=None,
num_filters=16,
kernel_size=(3, 3),
padding='SAME',
stride=(1, 1),
initializer=tf.contrib.layers.xavier_initializer(),
l2_strength=0.0,
bias=0.0,
activation=None,
batchnorm_enabled=False,
max_pool_enabled=False,
dropout_keep_prob=-1,
is_training=True):
"""
This block is responsible for a convolution 2D layer followed by optional (non-linearity, dropout, max-pooling).
Note that: "is_training" should be passed by a correct value based on being in either training or testing.
:param name: (string) 由tf.name_scope('name') as scope提供.
:param x: (tf.tensor)输入(N, H, W, C).
:param num_filters: (integer) No. of filters (输出的深度)
:param kernel_size: (integer tuple) 卷积核的大小.
:param padding: (string) padding的大小.
:param stride: (integer tuple) 步长.
:param initializer: (tf.contrib initializer) 初始化, He et al. normal or Xavier normal are recommended.
:param l2_strength:(weight decay) (float) L2 正则化参数.
:param bias: (float) 偏置.
:param activation: (tf.graph operator) 卷积运算后的激活函数. If None, linear is applied.
:param batchnorm_enabled: (boolean) for enabling batch normalization.
:param max_pool_enabled: (boolean) for enabling max-pooling 2x2 to decrease width and height by a factor of 2.
:param dropout_keep_prob: (float) 保持多少个神经元的概率. If equals -1, it means no dropout
:param is_training: (boolean) to diff. between training and testing (important for batch normalization and dropout)
:return: The output tensor of the layer (N, H', W', C').
"""
with tf.variable_scope(name) as scope:
conv_o_b = __conv2d_p(scope,
x=x,
w=w,
num_filters=num_filters,
kernel_size=kernel_size,
stride=stride,
padding=padding,
initializer=initializer,
l2_strength=l2_strength,
bias=bias)
if batchnorm_enabled:
conv_o_bn = tf.layers.batch_normalization(conv_o_b,
training=is_training)
if not activation:
conv_a = conv_o_bn
else:
conv_a = activation(conv_o_bn)
else:
if not activation:
conv_a = conv_o_b
else:
conv_a = activation(conv_o_b)
def dropout_with_keep():
return tf.nn.dropout(conv_a, dropout_keep_prob)
def dropout_no_keep():
return tf.nn.dropout(conv_a, 1.0)
if dropout_keep_prob != -1:
conv_o_dr = tf.cond(is_training, dropout_with_keep,
dropout_no_keep)
else:
conv_o_dr = conv_a
conv_o = conv_o_dr
if max_pool_enabled:
conv_o = max_pool_2d(conv_o_dr)
return conv_o