tf.raw_ops.FusedBatchNormV3

Batch normalization.

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.

x A Tensor. Must be one of the following types: half, bfloat16, float32. A 4D Tensor for input data.
scale A Tensor. Must be one of the following types: float32. A 1D Tensor for scaling factor, to scale the normalized x.
offset A Tensor. Must have the same type as scale. A 1D Tensor for offset, to shift to the normalized x.
mean A Tensor. Must have the same type as scale. A 1D Tensor for population mean. Used for inference only; must be empty for training.
variance A Tensor. Must have the same type as scale. A 1D Tensor for population variance. Used for inference only; must be empty for training.
epsilon An optional float. Defaults to 0.0001. A small float number added to the variance of x.
exponential_avg_factor An optional float. Defaults to 1.
data_format An optional string from: "NHWC", "NCHW", "NDHWC", "NCDHW". Defaults to "NHWC". The data format for x and y. 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).

A tuple of Tensor objects (y, batch_mean, batch_variance, reserve_space_1, reserve_space_2, reserve_space_3).
y A Tensor. Has the same type as x.
batch_mean A Tensor. Has the same type as scale.
batch_variance A Tensor. Has the same type as scale.
reserve_space_1 A Tensor. Has the same type as scale.
reserve_space_2 A Tensor. Has the same type as scale.
reserve_space_3 A Tensor. Has the same type as scale.