Gradients for Local Response Normalization.
tf.raw_ops.LRNGrad(
input_grads, input_image, output_image, depth_radius=5, bias=1, alpha=1,
beta=0.5, name=None
)
Args |
|---|
input_grads
|
A Tensor. Must be one of the following types: half, bfloat16, float32.
4-D with shape [batch, height, width, channels].
|
input_image
|
A Tensor. Must have the same type as input_grads.
4-D with shape [batch, height, width, channels].
|
output_image
|
A Tensor. Must have the same type as input_grads.
4-D with shape [batch, height, width, channels].
|
depth_radius
|
An optional int. Defaults to 5. A depth radius.
|
bias
|
An optional float. Defaults to 1.
An offset (usually > 0 to avoid dividing by 0).
|
alpha
|
An optional float. Defaults to 1.
A scale factor, usually positive.
|
beta
|
An optional float. Defaults to 0.5. An exponent.
|
name
|
A name for the operation (optional).
|
Returns |
|---|
A Tensor. Has the same type as input_grads.
|
