tensorflow::ops::FusedBatchNormGradV3

Gradient for 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.

Args:

• scope: A Scope object
• y_backprop: A 4D Tensor for the gradient with respect to y.
• x: A 4D Tensor for input data.
• scale: A 1D Tensor for scaling factor, to scale the normalized x.
• reserve_space_1: When is_training is True, a 1D Tensor for the computed batch mean to be reused in gradient computation. When is_training is False, a 1D Tensor for the population mean to be reused in both 1st and 2nd order gradient computation.
• reserve_space_2: When is_training is True, a 1D Tensor for the computed batch variance (inverted variance in the cuDNN case) to be reused in gradient computation. When is_training is False, a 1D Tensor for the population variance to be reused in both 1st and 2nd order gradient computation.
• reserve_space_3: When is_training is True, a 1D Tensor for some intermediate results to be reused in gradient computation. When is_training is False, a dummy empty Tensor will be created.

Optional attributes (see Attrs):

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

Returns:

• Output x_backprop: A 4D Tensor for the gradient with respect to x.
• Output scale_backprop: A 1D Tensor for the gradient with respect to scale.
• Output offset_backprop: A 1D Tensor for the gradient with respect to offset.
• Output reserve_space_4: Unused placeholder to match the mean input in FusedBatchNorm.
• Output reserve_space_5: Unused placeholder to match the variance input in FusedBatchNorm.

Public attributes

Public functions

Public static functions