tf.nn.conv2d 与 tf.layers.conv2d [英] tf.nn.conv2d vs tf.layers.conv2d

问题描述

使用 tf.nn.* 比使用 tf.layers.* 有什么优势吗?

Is there any advantage in using tf.nn.* over tf.layers.*?

例如，文档中的大多数示例都使用 tf.nn.conv2d，但不清楚为什么要这样做.

Most of the examples in the doc use tf.nn.conv2d, for instance, but it is not clear why they do so.

推荐答案

对于卷积，它们是一样的.更准确地说，tf.layers.conv2d(实际上是 _Conv)使用 tf.nn.convolution 作为后端.您可以遵循以下调用链:tf.layers.conv2d>Conv2D>Conv2D.apply()>_Conv>_Conv.apply()>_Layer.apply()>_Layer.\__call__()>_Conv.call()>nn.convolution()...

For convolution, they are the same. More precisely, tf.layers.conv2d (actually _Conv) uses tf.nn.convolution as the backend. You can follow the calling chain of: tf.layers.conv2d>Conv2D>Conv2D.apply()>_Conv>_Conv.apply()>_Layer.apply()>_Layer.\__call__()>_Conv.call()>nn.convolution()...

这篇关于tf.nn.conv2d 与 tf.layers.conv2d的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！