Gradients for batch normalization.
tf.raw_ops.BatchNormWithGlobalNormalizationGrad(
t, m, v, gamma, backprop, variance_epsilon, scale_after_normalization, name=None
)
This op is deprecated. See tf.nn.batch_normalization.
Args | |
|---|---|
t
|
A Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, complex64, int64, qint8, quint8, qint32, bfloat16, uint16, complex128, half, uint32, uint64.
A 4D input Tensor.
|
m
|
A Tensor. Must have the same type as t.
A 1D mean Tensor with size matching the last dimension of t.
This is the first output from tf.nn.moments,
or a saved moving average thereof.
|
v
|
A Tensor. Must have the same type as t.
A 1D variance Tensor with size matching the last dimension of t.
This is the second output from tf.nn.moments,
or a saved moving average thereof.
|
gamma
|
A Tensor. Must have the same type as t.
A 1D gamma Tensor with size matching the last dimension of t.
If "scale_after_normalization" is true, this Tensor will be multiplied
with the normalized Tensor.
|
backprop
|
A Tensor. Must have the same type as t. 4D backprop Tensor.
|
variance_epsilon
|
A float. A small float number to avoid dividing by 0.
|
scale_after_normalization
|
A bool.
A bool indicating whether the resulted tensor
needs to be multiplied with gamma.
|
name
|
A name for the operation (optional). |
Returns | |
|---|---|
A tuple of Tensor objects (dx, dm, dv, db, dg).
|
|
dx
|
A Tensor. Has the same type as t.
|
dm
|
A Tensor. Has the same type as t.
|
dv
|
A Tensor. Has the same type as t.
|
db
|
A Tensor. Has the same type as t.
|
dg
|
A Tensor. Has the same type as t.
|