tf.raw_ops.FusedBatchNormGradV3

Gradient for batch normalization.

View aliases

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.raw_ops.FusedBatchNormGradV3

tf.raw_ops.FusedBatchNormGradV3(
    y_backprop, x, scale, reserve_space_1, reserve_space_2, reserve_space_3,
    epsilon=0.0001, data_format='NHWC', is_training=True, name=None
)

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
y_backprop	A Tensor. Must be one of the following types: half, bfloat16, float32. A 4D Tensor for the gradient with respect to y.
x	A Tensor. Must have the same type as y_backprop. A 4D Tensor for input data.
scale	A Tensor of type float32. A 1D Tensor for scaling factor, to scale the normalized x.
reserve_space_1	A Tensor. Must be one of the following types: float32. 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	A Tensor. Must have the same type as reserve_space_1. 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	A Tensor. Must have the same type as reserve_space_1. 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.
epsilon	An optional float. Defaults to 0.0001. A small float number added to the variance of x.
data_format	An optional string from: "NHWC", "NCHW", "NDHWC", "NCDHW". Defaults to "NHWC". The data format for y_backprop, x, x_backprop. Either "NHWC" (default) or "NCHW".
is_training	An optional bool. Defaults to True. A bool value to indicate the operation is for training (default) or inference.
name	A name for the operation (optional).

Returns
A tuple of Tensor objects (x_backprop, scale_backprop, offset_backprop, reserve_space_4, reserve_space_5).
x_backprop	A Tensor. Has the same type as y_backprop.
scale_backprop	A Tensor. Has the same type as reserve_space_1.
offset_backprop	A Tensor. Has the same type as reserve_space_1.
reserve_space_4	A Tensor. Has the same type as reserve_space_1.
reserve_space_5	A Tensor. Has the same type as reserve_space_1.