tensorflow::ops::FusedBatchNorm

Batch normalization.

Summary

Note that the size of 4D Tensors are defined by either "NHWC" or "NCHW". The size of 1D Tensors matches the dimension C of the 4D Tensors.

Arguments:

• scope: A Scope object
• x: A 4D Tensor for input data.
• scale: A 1D Tensor for scaling factor, to scale the normalized x.
• offset: A 1D Tensor for offset, to shift to the normalized x.
• mean: A 1D Tensor for population mean. Used for inference only; must be empty for training.
• variance: A 1D Tensor for population variance. Used for inference only; must be empty for training.

Optional attributes (see Attrs):

• epsilon: A small float number added to the variance of x.
• data_format: The data format for x and y. Either "NHWC" (default) or "NCHW".
• is_training: A bool value to indicate the operation is for training (default) or inference.

Returns:

• Output y: A 4D Tensor for output data.
• Output batch_mean: A 1D Tensor for the computed batch mean, to be used by TensorFlow to compute the running mean.
• Output batch_variance: A 1D Tensor for the computed batch variance, to be used by TensorFlow to compute the running variance.
• Output reserve_space_1: A 1D Tensor for the computed batch mean, to be reused in the gradient computation.
• Output reserve_space_2: A 1D Tensor for the computed batch variance (inverted variance in the cuDNN case), to be reused in the gradient computation.

Public attributes

::tensorflow::Output batch_mean

::tensorflow::Output batch_variance

Operation operation

::tensorflow::Output reserve_space_1

::tensorflow::Output reserve_space_2

::tensorflow::Output y

 FusedBatchNorm(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input x,
  ::tensorflow::Input scale,
  ::tensorflow::Input offset,
  ::tensorflow::Input mean,
  ::tensorflow::Input variance
)

 FusedBatchNorm(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input x,
  ::tensorflow::Input scale,
  ::tensorflow::Input offset,
  ::tensorflow::Input mean,
  ::tensorflow::Input variance,
  const FusedBatchNorm::Attrs & attrs
)

Attrs DataFormat(
  StringPiece x
)

Attrs Epsilon(
  float x
)

Attrs IsTraining(
  bool x
)