tensorflow Using Batch Normalization


contrib.layers.batch_norm paramsRemarks
betapython bool type. Whether or not to center the moving_mean and moving_variance
gammapython bool type. Whether or not to scale the moving_mean and moving_variance
is_trainingAccepts python bool or TensorFlow tf.palceholder(tf.bool)
decayThe default setting is decay=0.999. A smaller value (i.e. decay=0.9) is better for smaller dataset and/or less training steps.


Here is a screen shot of the result of the working example above.

screen shot of running results

The code and a jupyter notebook version of this working example can be found at the author's repository