Python tensorflow 模块，Varialbe() 实例源码

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)

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