tf.raw_ops.LRNGrad

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
)

input_gradsA Tensor. Must be one of the following types: half, bfloat16, float32. 4-D with shape [batch, height, width, channels].
input_imageA Tensor. Must have the same type as input_grads. 4-D with shape [batch, height, width, channels].
output_imageA Tensor. Must have the same type as input_grads. 4-D with shape [batch, height, width, channels].
depth_radiusAn optional int. Defaults to 5. A depth radius.
biasAn optional float. Defaults to 1. An offset (usually > 0 to avoid dividing by 0).
alphaAn optional float. Defaults to 1. A scale factor, usually positive.
betaAn optional float. Defaults to 0.5. An exponent.
nameA name for the operation (optional).

A Tensor. Has the same type as input_grads.