Python tensorflow.Varialbe() Examples

The following are 30 code examples of tensorflow.Varialbe(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorflow , or try the search function .
Example #1
Source File: tf_util.py    From ASIS with MIT License 6 votes vote down vote up 
def batch_norm_for_conv2d(inputs, is_training, bn_decay, scope, is_dist=False):
  """ 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
      is_dist:     true indicating distributed training scheme
  Return:
      normed:      batch-normalized maps
  """
  if is_dist:
    return batch_norm_dist_template(inputs, is_training, scope, [0,1,2], bn_decay)
  else:
    return batch_norm_template(inputs, is_training, scope, [0,1,2], bn_decay)
Example #2
Source File: tf_util.py    From GSPN with MIT License 6 votes vote down vote up 
def batch_norm_template(inputs, is_training, scope, moments_dims_unused, bn_decay, data_format='NHWC'):
  """ 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
      data_format:   'NHWC' or 'NCHW'
  Return:
      normed:        batch-normalized maps
  """
  bn_decay = bn_decay if bn_decay is not None else 0.9
  return tf.contrib.layers.batch_norm(inputs, 
                                      center=True, scale=True,
                                      is_training=is_training, decay=bn_decay,updates_collections=None,
                                      scope=scope, reuse=False,
                                      data_format=data_format)
Example #3
Source File: tf_util.py    From SpiderCNN with MIT License 6 votes vote down vote up 
def batch_norm_template_multiGPU(inputs, is_training, scope, moments_dims_unused, bn_decay, data_format='NHWC'):
  """ 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
      data_format:   'NHWC' or 'NCHW'
  Return:
      normed:        batch-normalized maps
  """
  bn_decay = bn_decay if bn_decay is not None else 0.9
  return tf.contrib.layers.batch_norm(inputs, 
                                      center=True, scale=True,
                                      is_training=is_training, decay=bn_decay,updates_collections=None,
                                      scope=scope,
                                      data_format=data_format)
Example #4
Source File: tf_util.py    From ASIS with MIT License 6 votes vote down vote up 
def batch_norm_for_fc(inputs, is_training, bn_decay, scope, is_dist=False):
  """ 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
      is_dist:     true indicating distributed training scheme
  Return:
      normed:      batch-normalized maps
  """
  if is_dist:
    return batch_norm_dist_template(inputs, is_training, scope, [0,], bn_decay)
  else:
    return batch_norm_template(inputs, is_training, scope, [0,], bn_decay)
Example #5
Source File: tf_util_dgcnn.py    From AlignNet-3D with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up 
def batch_norm_for_fc(inputs, is_training, bn_decay, scope, is_dist=False):
  """ 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
      is_dist:     true indicating distributed training scheme
  Return:
      normed:      batch-normalized maps
  """
  if is_dist:
    return batch_norm_dist_template(inputs, is_training, scope, [0,], bn_decay)
  else:
    return batch_norm_template(inputs, is_training, scope, [0,], bn_decay)
Example #6
Source File: tf_util.py    From reading-frustum-pointnets-code with Apache License 2.0 6 votes vote down vote up 
def batch_norm_template(inputs, is_training, scope, moments_dims_unused, bn_decay, data_format='NHWC'):
  """ 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
      data_format:   'NHWC' or 'NCHW'
  Return:
      normed:        batch-normalized maps
  """
  bn_decay = bn_decay if bn_decay is not None else 0.9
  return tf.contrib.layers.batch_norm(inputs, 
                                      center=True, scale=True,
                                      is_training=is_training, decay=bn_decay,updates_collections=None,
                                      scope=scope,
                                      data_format=data_format)
Example #7
Source File: tf_util_dgcnn.py    From AlignNet-3D with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up 
def batch_norm_for_conv1d(inputs, is_training, bn_decay, scope, is_dist=False):
  """ 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
      is_dist:     true indicating distributed training scheme
  Return:
      normed:      batch-normalized maps
  """
  if is_dist:
    return batch_norm_dist_template(inputs, is_training, scope, [0,1], bn_decay)
  else:
    return batch_norm_template(inputs, is_training, scope, [0,1], bn_decay)
Example #8
Source File: tf_util_dgcnn.py    From AlignNet-3D with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up 
def batch_norm_for_conv2d(inputs, is_training, bn_decay, scope, is_dist=False):
  """ 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
      is_dist:     true indicating distributed training scheme
  Return:
      normed:      batch-normalized maps
  """
  if is_dist:
    return batch_norm_dist_template(inputs, is_training, scope, [0,1,2], bn_decay)
  else:
    return batch_norm_template(inputs, is_training, scope, [0,1,2], bn_decay)
Example #9
Source File: tf_util_dgcnn.py    From AlignNet-3D with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up 
def batch_norm_for_conv3d(inputs, is_training, bn_decay, scope, is_dist=False):
  """ 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
      is_dist:     true indicating distributed training scheme
  Return:
      normed:      batch-normalized maps
  """
  if is_dist:
    return batch_norm_dist_template(inputs, is_training, scope, [0,1,2,3], bn_decay)
  else:
    return batch_norm_template(inputs, is_training, scope, [0,1,2,3], bn_decay)
Example #10
Source File: tf_util.py    From ASIS with MIT License 6 votes vote down vote up 
def batch_norm_for_conv1d(inputs, is_training, bn_decay, scope, is_dist=False):
  """ 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
      is_dist:     true indicating distributed training scheme
  Return:
      normed:      batch-normalized maps
  """
  if is_dist:
    return batch_norm_dist_template(inputs, is_training, scope, [0,1], bn_decay)
  else:
    return batch_norm_template(inputs, is_training, scope, [0,1], bn_decay)
Example #11
Source File: tf_util.py    From SPFN with MIT License 6 votes vote down vote up 
def batch_norm_template(inputs, is_training, scope, moments_dims_unused, bn_decay, data_format='NHWC'):
  """ 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
      data_format:   'NHWC' or 'NCHW'
  Return:
      normed:        batch-normalized maps
  """
  bn_decay = bn_decay if bn_decay is not None else 0.9
  return tf.contrib.layers.batch_norm(inputs, 
                                      center=True, scale=True,
                                      is_training=is_training, decay=bn_decay,updates_collections=None,
                                      scope=scope,
                                      data_format=data_format)
Example #12
Source File: tf_util.py    From deep-functional-dictionaries with MIT License 6 votes vote down vote up 
def batch_norm_template(inputs, is_training, scope, moments_dims_unused, bn_decay, data_format='NHWC'):
  """ 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
      data_format:   'NHWC' or 'NCHW'
  Return:
      normed:        batch-normalized maps
  """
  bn_decay = bn_decay if bn_decay is not None else 0.9
  return tf.contrib.layers.batch_norm(inputs, 
                                      center=True, scale=True,
                                      is_training=is_training, decay=bn_decay,updates_collections=None,
                                      scope=scope,
                                      data_format=data_format)
Example #13
Source File: tf_util.py    From Geo-CNN with Apache License 2.0 6 votes vote down vote up 
def batch_norm_template(inputs, is_training, scope, moments_dims_unused, bn_decay, data_format='NHWC'):
  """ 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
      data_format:   'NHWC' or 'NCHW'
  Return:
      normed:        batch-normalized maps
  """
  bn_decay = bn_decay if bn_decay is not None else 0.9
  return tf.contrib.layers.batch_norm(inputs, 
                                      center=True, scale=True,
                                      is_training=is_training, decay=bn_decay,updates_collections=None,
                                      scope=scope,
                                      data_format=data_format)
Example #14
Source File: nn_functions.py    From AmusingPythonCodes with MIT License 6 votes vote down vote up 
def batch_normalization(x, out_shape, phase_train):
    """Batch normalization on convolutional maps.
    Args:
        x:           Tensor, 4D Batch-Height-Width-Depth (BHWD) input maps
        out_shape:   integer, depth of input maps
        phase_train: boolean tf.Varialbe, true indicates training phase
    Return:
        normed:      batch-normalized maps
    """
    with tf.variable_scope('batch_norm'):
        beta = tf.Variable(tf.constant(0.0, shape=[out_shape]), name='beta', trainable=True)
        gamma = tf.Variable(tf.constant(1.0, shape=[out_shape]), 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
Example #15
Source File: architecture.py    From DCNets with MIT License 5 votes vote down vote up 
def batch_norm(self, x, n_out, phase_train):
        """
        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'):

            gamma = self.get_bias(n_out, 1.0, 'gamma')
            beta = self.get_bias(n_out, 0.0, 'beta')

            batch_mean, batch_var = tf.nn.moments(x, [0,1,2], name='moments')
            ema = tf.train.ExponentialMovingAverage(decay=0.999)

            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)))
            return tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
Example #16
Source File: tf_util.py    From GSPN with MIT License 5 votes vote down vote up 
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)
Example #17
Source File: architecture.py    From DCNets with MIT License 5 votes vote down vote up 
def xnorm_batch_norm(self, x, phase_train):
        """
        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('xnorm_bn'):

            batch_mean = tf.reduce_mean(x, [0,1,2])
            ema = tf.train.ExponentialMovingAverage(decay=0.999)

            def mean_var_with_update():
                ema_apply_op = ema.apply([batch_mean])
                with tf.control_dependencies([ema_apply_op]):
                    return tf.identity(batch_mean)

            mean = tf.cond(phase_train,
                                mean_var_with_update,
                                lambda: (ema.average(batch_mean)))
            return mean
Example #18
Source File: architecture.py    From DCNets with MIT License 5 votes vote down vote up 
def xnorm_batch_norm(self, x, phase_train):
        """
        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('xnorm_bn'):

            batch_mean = tf.reduce_mean(x, [0,1,2])
            ema = tf.train.ExponentialMovingAverage(decay=0.999)

            def mean_var_with_update():
                ema_apply_op = ema.apply([batch_mean])
                with tf.control_dependencies([ema_apply_op]):
                    return tf.identity(batch_mean)

            mean = tf.cond(phase_train,
                                mean_var_with_update,
                                lambda: (ema.average(batch_mean)))
            return mean
Example #19
Source File: architecture.py    From DCNets with MIT License 5 votes vote down vote up 
def batch_norm(self, x, n_out, phase_train):
        """
        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'):

            gamma = self.get_bias(n_out, 1.0, 'gamma')
            beta = self.get_bias(n_out, 0.0, 'beta')

            batch_mean, batch_var = tf.nn.moments(x, [0,1,2], name='moments')
            ema = tf.train.ExponentialMovingAverage(decay=0.999)

            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)))
            return tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
Example #20
Source File: architecture.py    From DCNets with MIT License 5 votes vote down vote up 
def xnorm_batch_norm(self, x, phase_train):
        """
        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('xnorm_bn'):

            batch_mean = tf.reduce_mean(x, [0,1,2])
            ema = tf.train.ExponentialMovingAverage(decay=0.999)

            def mean_var_with_update():
                ema_apply_op = ema.apply([batch_mean])
                with tf.control_dependencies([ema_apply_op]):
                    return tf.identity(batch_mean)

            mean = tf.cond(phase_train,
                                mean_var_with_update,
                                lambda: (ema.average(batch_mean)))
            return mean
Example #21
Source File: tf_util.py    From Geo-CNN with Apache License 2.0 5 votes vote down vote up 
def batch_norm_for_conv1d(inputs, is_training, bn_decay, scope, data_format):
  """ 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
      data_format: 'NHWC' or 'NCHW'
  Return:
      normed:      batch-normalized maps
  """
  return batch_norm_template(inputs, is_training, scope, [0,1], bn_decay, data_format)
Example #22
Source File: tf_util.py    From SpiderCNN with MIT License 5 votes vote down vote up 
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
Example #23
Source File: architecture.py    From MHE with MIT License 5 votes vote down vote up 
def batch_norm(self, x, n_out, phase_train):
        """
        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'):

            gamma = self.get_bias(n_out, 1.0, 'gamma')
            beta = self.get_bias(n_out, 0.0, 'beta')

            batch_mean, batch_var = tf.nn.moments(x, [0,1,2], name='moments')
            ema = tf.train.ExponentialMovingAverage(decay=0.999)

            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)))
            return tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
Example #24
Source File: tf_util.py    From pointnetvlad with MIT License 5 votes vote down vote up 
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)
Example #25
Source File: tf_util.py    From pointnetvlad with MIT License 5 votes vote down vote up 
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)
Example #26
Source File: tf_util.py    From pointnetvlad with MIT License 5 votes vote down vote up 
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)
Example #27
Source File: tf_util.py    From pointnetvlad with MIT License 5 votes vote down vote up 
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)
Example #28
Source File: tf_util.py    From pointnetvlad with MIT License 5 votes vote down vote up 
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
Example #29
Source File: tf_util.py    From Geo-CNN with Apache License 2.0 5 votes vote down vote up 
def batch_norm_for_conv2d(inputs, is_training, bn_decay, scope, data_format):
  """ 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
      data_format: 'NHWC' or 'NCHW'
  Return:
      normed:      batch-normalized maps
  """
  return batch_norm_template(inputs, is_training, scope, [0,1,2], bn_decay, data_format)
Example #30
Source File: nn_layers.py    From DeepLoc with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
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