tf.raw_ops.FusedBatchNorm

Batch normalization.

View aliases

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.raw_ops.FusedBatchNorm

tf.raw_ops.FusedBatchNorm(
    x, scale, offset, mean, variance, epsilon=0.0001, exponential_avg_factor=1,
    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
x	A Tensor. Must be one of the following types: float32. A 4D Tensor for input data.
scale	A Tensor. Must have the same type as x. A 1D Tensor for scaling factor, to scale the normalized x.
offset	A Tensor. Must have the same type as x. A 1D Tensor for offset, to shift to the normalized x.
mean	A Tensor. Must have the same type as x. A 1D Tensor for population mean. Used for inference only; must be empty for training.
variance	A Tensor. Must have the same type as x. 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". 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).

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