TensorFlow:为什么avg_pool忽略一个跨度维度？

Question

我试图跨越渠道维度,以下代码表现出令人惊讶的行为.我希望tf.nn.max_pool并且tf.nn.avg_pool在输入完全相同的参数时应该产生相同形状的张量.不是这种情况.

import tensorflow as tf

x = tf.get_variable('x', shape=(100, 32, 32, 64),
        initializer=tf.constant_initializer(5), dtype=tf.float32)
ksize = (1, 2, 2, 2)
strides = (1, 2, 2, 2)
max_pool = tf.nn.max_pool(x, ksize, strides, padding='SAME')
avg_pool = tf.nn.avg_pool(x, ksize, strides, padding='SAME')
print(max_pool.shape)
print(avg_pool.shape)

这打印

$ python ex04/mini.py 
(100, 16, 16, 32)
(100, 16, 16, 64)

显然,我误解了一些事情.

Answer 1

事实证明这确实是一个错误。 https://github.com/tensorflow/tensorflow/issues/14886#issuecomment-352934112