tf.nn.local_response_normalization
tf.nn.local_response_normalization
tf.nn.local_response_normalization
tf.nn.lrn
local_response_normalization( input, depth_radius=None, bias=None, alpha=None, beta=None, name=None )
Defined in tensorflow/python/ops/gen_nn_ops.py
.
See the guide: Neural Network > Normalization
Local Response Normalization.
The 4-D input
tensor is treated as a 3-D array of 1-D vectors (along the last dimension), and each vector is normalized independently. Within a given vector, each component is divided by the weighted, squared sum of inputs within depth_radius
. In detail,
sqr_sum[a, b, c, d] = sum(input[a, b, c, d - depth_radius : d + depth_radius + 1] ** 2) output = input / (bias + alpha * sqr_sum) ** beta
For details, see Krizhevsky et al., ImageNet classification with deep convolutional neural networks (NIPS 2012).
Args:
-
input
: ATensor
. Must be one of the following types:float32
,half
. 4-D. -
depth_radius
: An optionalint
. Defaults to5
. 0-D. Half-width of the 1-D normalization window. -
bias
: An optionalfloat
. Defaults to1
. An offset (usually positive to avoid dividing by 0). -
alpha
: An optionalfloat
. Defaults to1
. A scale factor, usually positive. -
beta
: An optionalfloat
. Defaults to0.5
. An exponent. -
name
: A name for the operation (optional).
Returns:
A Tensor
. Has the same type as input
.
© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/nn/local_response_normalization