def batch_norm(in_tensor, phase_train, name, reuse=None, data_format='NHWC', center=True, scale=True):
"""
Batch normalization on convolutional maps.
Ref.: http://stackoverflow.com/questions/33949786/how-could-i-use-batch-normalization-in-tensorflow
Args:
x: Tensor, 4D BHWD input maps
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
axis = -1 if data_format == 'NHWC' else 1
with tf.variable_scope(name):
# return tf.contrib.layers.batch_norm(in_tensor, is_training=phase_train, scope=scope, reuse=reuse)
return tf.layers.batch_normalization(in_tensor, axis=axis, center=center, scale=scale, training=phase_train,
reuse=reuse, fused=True, momentum=0.99)
python类Varialbe()的实例源码
def batch_norm_template(inputs, is_training, scope, moments_dims, bn_decay):
""" Batch normalization on convolutional maps and beyond...
Ref.: http://stackoverflow.com/questions/33949786/how-could-i-use-batch-normalization-in-tensorflow
Args:
inputs: Tensor, k-D input ... x C could be BC or BHWC or BDHWC
is_training: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
moments_dims: a list of ints, indicating dimensions for moments calculation
bn_decay: float or float tensor variable, controling moving average weight
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope) as sc:
num_channels = inputs.get_shape()[-1].value
beta = tf.Variable(tf.constant(0.0, shape=[num_channels]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[num_channels]),
name='gamma', trainable=True)
batch_mean, batch_var = tf.nn.moments(inputs, moments_dims, name='moments')
decay = bn_decay if bn_decay is not None else 0.9
ema = tf.train.ExponentialMovingAverage(decay=decay)
# Operator that maintains moving averages of variables.
ema_apply_op = tf.cond(is_training,
lambda: ema.apply([batch_mean, batch_var]),
lambda: tf.no_op())
# Update moving average and return current batch's avg and var.
def mean_var_with_update():
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
# ema.average returns the Variable holding the average of var.
mean, var = tf.cond(is_training,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(inputs, mean, var, beta, gamma, 1e-3)
return normed
def batch_norm_for_fc(inputs, is_training, bn_decay, scope):
""" Batch normalization on FC data.
Args:
inputs: Tensor, 2D BxC input
is_training: boolean tf.Varialbe, true indicates training phase
bn_decay: float or float tensor variable, controling moving average weight
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
return batch_norm_template(inputs, is_training, scope, [0,], bn_decay)
def batch_norm_for_conv1d(inputs, is_training, bn_decay, scope):
""" Batch normalization on 1D convolutional maps.
Args:
inputs: Tensor, 3D BLC input maps
is_training: boolean tf.Varialbe, true indicates training phase
bn_decay: float or float tensor variable, controling moving average weight
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
return batch_norm_template(inputs, is_training, scope, [0,1], bn_decay)
def batch_norm_for_conv2d(inputs, is_training, bn_decay, scope):
""" Batch normalization on 2D convolutional maps.
Args:
inputs: Tensor, 4D BHWC input maps
is_training: boolean tf.Varialbe, true indicates training phase
bn_decay: float or float tensor variable, controling moving average weight
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
return batch_norm_template(inputs, is_training, scope, [0,1,2], bn_decay)
def batch_norm_for_conv3d(inputs, is_training, bn_decay, scope):
""" Batch normalization on 3D convolutional maps.
Args:
inputs: Tensor, 5D BDHWC input maps
is_training: boolean tf.Varialbe, true indicates training phase
bn_decay: float or float tensor variable, controling moving average weight
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
return batch_norm_template(inputs, is_training, scope, [0,1,2,3], bn_decay)
def batch_norm(x, n_out, phase_train, conv=True, scope='bn'):
"""
Batch normalization on convolutional maps.
Args:
x: Tensor, 4D BHWD input maps
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope):
beta = tf.Variable(tf.constant(0.0, shape=[n_out]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[n_out]),
name='gamma', trainable=True)
if conv:
batch_mean, batch_var = tf.nn.moments(x, [0,1,2], name='moments')
else:
batch_mean, batch_var = tf.nn.moments(x, [0], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
def batch_norm(x, n_out, phase_train, scope='bn'):
"""
Batch normalization on convolutional maps.
Args:
x: Tensor
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope):
beta = tf.Variable(tf.constant(0.0, shape=[n_out]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[n_out]),
name='gamma', trainable=True)
batch_mean, batch_var = tf.nn.moments(x, [0], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
def batch_norm(x, n_out, phase_train, scope='bn'):
"""
Batch normalization on convolutional maps.
Args:
x: Tensor
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope):
beta = tf.Variable(tf.constant(0.0, shape=[n_out]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[n_out]),
name='gamma', trainable=True)
batch_mean, batch_var = tf.nn.moments(x, [0], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
def batch_norm(x, n_out, phase_train, scope='bn'):
"""
Batch normalization on convolutional maps.
Args:
x: Tensor
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope):
beta = tf.Variable(tf.constant(0.0, shape=[n_out]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[n_out]),
name='gamma', trainable=True)
batch_mean, batch_var = tf.nn.moments(x, [0], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
def batch_norm(x, n_out, phase_train, scope='bn'):
"""
Batch normalization on convolutional maps.
Args:
x: Tensor
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope):
beta = tf.Variable(tf.constant(0.0, shape=[n_out]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[n_out]),
name='gamma', trainable=True)
batch_mean, batch_var = tf.nn.moments(x, [0], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
def batch_norm(x, n_out, phase_train, scope='bn'):
"""
Batch normalization on convolutional maps.
Args:
x: Tensor
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope):
beta = tf.Variable(tf.constant(0.0, shape=[n_out]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[n_out]),
name='gamma', trainable=True)
batch_mean, batch_var = tf.nn.moments(x, [0], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
def batch_norm(x, n_out, phase_train, scope='bn'):
"""
Batch normalization on convolutional maps.
Args:
x: Tensor
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope):
beta = tf.Variable(tf.constant(0.0, shape=[n_out]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[n_out]),
name='gamma', trainable=True)
batch_mean, batch_var = tf.nn.moments(x, [0], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
def batch_norm(x, n_out, phase_train=tf.constant(True)):
"""
Batch normalization on convolutional maps.
Ref.: http://stackoverflow.com/questions/33949786/how-could-i-use-batch-normalization-in-tensorflow
Args:
x: Tensor, 4D BHWD input maps
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope('bn'):
beta = tf.Variable(tf.constant(0.0, shape=[n_out]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[n_out]),
name='gamma', trainable=True)
batch_mean, batch_var = tf.nn.moments(x, [0, 1, 2], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
def batch_norm_for_fc(inputs, is_training, bn_decay, scope):
""" Batch normalization on FC data.
Args:
inputs: Tensor, 2D BxC input
is_training: boolean tf.Varialbe, true indicates training phase
bn_decay: float or float tensor variable, controling moving average weight
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
return batch_norm_template(inputs, is_training, scope, [0,], bn_decay)
def batch_norm_for_conv1d(inputs, is_training, bn_decay, scope):
""" Batch normalization on 1D convolutional maps.
Args:
inputs: Tensor, 3D BLC input maps
is_training: boolean tf.Varialbe, true indicates training phase
bn_decay: float or float tensor variable, controling moving average weight
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
return batch_norm_template(inputs, is_training, scope, [0,1], bn_decay)
def batch_norm_for_conv2d(inputs, is_training, bn_decay, scope):
""" Batch normalization on 2D convolutional maps.
Args:
inputs: Tensor, 4D BHWC input maps
is_training: boolean tf.Varialbe, true indicates training phase
bn_decay: float or float tensor variable, controling moving average weight
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
return batch_norm_template(inputs, is_training, scope, [0,1,2], bn_decay)
def batch_norm_for_conv3d(inputs, is_training, bn_decay, scope):
""" Batch normalization on 3D convolutional maps.
Args:
inputs: Tensor, 5D BDHWC input maps
is_training: boolean tf.Varialbe, true indicates training phase
bn_decay: float or float tensor variable, controling moving average weight
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
return batch_norm_template(inputs, is_training, scope, [0,1,2,3], bn_decay)
def batch_norm_conv(x, n_out, phase_train, scope='bn'):
"""
Batch normalization on convolutional maps.
Args:
x: Tensor, 4D BHWD input maps
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope):
beta = tf.Variable(tf.constant(0.0, shape=[n_out]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[n_out]),
name='gamma', trainable=True)
batch_mean, batch_var = tf.nn.moments(x, [0,1,2], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
def batch_norm_fc(x, n_out, phase_train, scope='bn'):
"""
Batch normalization on convolutional maps.
Args:
x: Tensor, 4D BHWD input maps
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope):
beta = tf.Variable(tf.constant(0.0, shape=[n_out]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[n_out]),
name='gamma', trainable=True)
batch_mean, batch_var = tf.nn.moments(x, [0], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
def batch_norm(input_tensor, if_training):
"""
Batch normalization on convolutional feature maps.
Ref.: http://stackoverflow.com/questions/33949786/how-could-i-use-batch-normalization-in-tensorflow
Args:
input_tensor: Tensor, 4D NHWC input feature maps
depth: Integer, depth of input feature maps
if_training: Boolean tf.Varialbe, true indicates training phase
scope: String, variable scope
Return:
normed_tensor: Batch-normalized feature maps
"""
with tf.variable_scope('batch_normalization'):
depth = int(input_tensor.get_shape()[-1])
beta = tf.Variable(tf.constant(0.0, shape=[depth]),
name='beta', trainable=True)
gamma = tf.Variable(tf.constant(1.0, shape=[depth]),
name='gamma', trainable=True)
batch_mean, batch_var = tf.nn.moments(input_tensor, [0,1,2], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.99)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(if_training,
mean_var_with_update,
lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed_tensor = tf.nn.batch_normalization(input_tensor, mean, var, beta, gamma, 1e-3)
return normed_tensor
