How to do Xavier initialization on TensorFlow

python tensorflow
Alejandro picture Alejandro · Nov 10, 2015 · Viewed 96.7k times · Source

I'm porting my Caffe network over to TensorFlow but it doesn't seem to have xavier initialization. I'm using truncated_normal but this seems to be making it a lot harder to train.

Answer

Sung Kim picture Sung Kim · Apr 22, 2016

Since version 0.8 there is a Xavier initializer, see here for the docs.

You can use something like this:

W = tf.get_variable("W", shape=[784, 256],
           initializer=tf.contrib.layers.xavier_initializer())

Related questions

How to find which version of TensorFlow is installed in my system?

I need to find which version of TensorFlow I have installed. I'm using Ubuntu 16.04 Long Term Support.

Read More
TensorFlow not found using pip

I'm trying to intstall TensorFlow using pip: $ pip install tensorflow --user Collecting tensorflow Could not find a version that satisfies the requirement tensorflow (from versions: ) No matching distribution found for tensorflow What am I doing wrong? So far I've used …

Read More
How to tell if tensorflow is using gpu acceleration from inside python shell?

I have installed tensorflow in my ubuntu 16.04 using the second answer here with ubuntu's builtin apt cuda installation. Now my question is how can I test if tensorflow is really using gpu? I have a gtx 960m gpu. When I …

Read More