在tf.layers.conv2d中，use_bias = True，这些偏差是捆绑在一起还是不捆绑在一起？
[英]In tf.layers.conv2d, with use_bias=True, are the biases tied or untied?
问题描述
One more question: 
还有一个问题：
If they are tied biases, how can I implement untied biases? 如果它们是有偏见的偏见，我该如何实施不受束缚的偏见？
I am using tensorflow 1.10.0 in python. 我在python中使用tensorflow 1.10.0。
1 个解决方案
解决方案1
0 已采纳 2018-08-30 03:56:15
tied biases is used in tf.layers.conv2d . 捆绑偏差用于tf.layers.conv2d 。
If you want united biases, just turn off use_bias and create bias variable manually with tf.Variable or tf.get_variable same shape with following feature map, finally sum them up. 如果您想要统一的偏置，只需关闭use_bias并使用tf.Variable或tf.get_variable相同形状并带有以下特征图的手动创建偏置变量，最后将它们汇总即可。
声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.
相关问题
tf.layers.conv2d和tf.layers.Conv2D有什么区别？ - What is difference between tf.layers.conv2d and tf.layers.Conv2D?
从 tf.layers.conv2d 理解输入/输出张量 - Understanding input/output tensors from tf.layers.conv2d
tf.layers.conv1d与tf.layers.conv2d之间的区别 - Difference between tf.layers.conv1d vs tf.layers.conv2d
tf.nn.conv2d 与 tf.layers.conv2d - tf.nn.conv2d vs tf.layers.conv2d
Tensorflow：为什么tf.nn.conv2d运行得比tf.layers.conv2d快？ - Tensorflow: why tf.nn.conv2d runs faster than tf.layers.conv2d?
tf.layers.conv2d 和 tf.contrib.slim.conv2d 的区别 - Difference between tf.layers.conv2d and tf.contrib.slim.conv2d
tensorflowjs：如何在编写 tensorflowjs 自定义层时扩展 tf.layers.conv2d - tensorflowjs: How to extends tf.layers.conv2d when writing tensorflowjs custom layers
“ tf.layers.conv2d”和“ tf.nn.softmax”不会更改尺寸 - “tf.layers.conv2d” and “tf.nn.softmax” don't change the dimension
使用tf.layers.conv2d时如何将跨步设置为零 - how to set stride to zero when using tf.layers.conv2d
Tensorflow-使用tf.contrib.layers.conv2d时，我可以设置权重和偏差的名称吗？ - Tensorflow - When using tf.contrib.layers.conv2d, can I set the name of the weights and biases?
相关标签