tf.nn.lrn() 方法有什么作用？

这是 cifar10-tutorial 中的代码片段。它来自 cifar 10.py。

# conv1
with tf.variable_scope('conv1') as scope:
kernel = _variable_with_weight_decay('weights', shape=[5, 5, 3, 64],
                                     stddev=1e-4, wd=0.0)
conv = tf.nn.conv2d(images, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.0))
bias = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv1)

# pool1
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
                     padding='SAME', name='pool1')
# norm1
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
                name='norm1')

tf.nn.lrn 方法有什么作用？我在 API 文档中找不到定义https://www.tensorflow.org/versions/r0.8/api_docs/python/index.html https://www.tensorflow.org/versions/r0.8/api_docs/python/index.html

tf.nn.lrn是一个缩写tf.nn.local_response_normalization。 因此，您可能需要查看的文档是：https://www.tensorflow.org/api_docs/python/tf/nn/local_response_normalization https://www.tensorflow.org/api_docs/python/tf/nn/local_response_normalization