Why do we name variables in Tensorflow?
摘要:Reference:Stack Overflow。 The name parameter is optional (you can create variables and constants with or without it), and the variable you use in your
阅读全文
posted @
2018-12-16 17:05
MicN
阅读(146)
推荐(0)
TF_Variable Sharing
摘要:Reference: http://jermmy.github.io/2017/08/25/2017-8-25-learn-tensorflow-shared-variables/ Tensorflow doesn't know what nodes should be grouped togeth
阅读全文
posted @
2018-07-24 09:43
MicN
阅读(176)
推荐(0)
TensorFlow 拾遗
摘要:1、、Here None in placeholder means that a dimension can be of any length. 2、、 3、、 4、、 5、、 tf.multiply( x, y, name=None )Returns x * y element-wise. tf.
阅读全文
posted @
2018-07-22 09:55
MicN
阅读(137)
推荐(0)
TF_RNNCell
摘要:参考:链接。 RNNCell BasicRNNCell GRUCell BasicLSTMCell LSTMCell MultiRNNCell 抽象类RNNCell 所有的rnncell均继承于RNNCell, RNNCell主要定义了几个抽象方法: 上述方法,__call__在对象被使用时调用,其
阅读全文
posted @
2018-06-07 21:22
MicN
阅读(500)
推荐(0)
TF启程
摘要:我第一次开始接触到TensorFlow大概是去年五月份,大三下,如果一年多已过,我却还在写启程。。这进度,实在汗颜。。 一个完整的tensorflow程序可以分为以下几部分: Inputs and Placeholders Build the Graph Inference Loss Trainin
阅读全文
posted @
2018-06-06 22:03
MicN
阅读(178)
推荐(0)