Does batchNormalizationLayer influence network results?

2 views (last 30 days)
As far as I know, batchnormalization is used for speeding up model training, it does not influence network results too much. However, the model training failed after i adding them. what is strange is that it is ok when i removed them. the both results are as follows:
with batchNormalizationLayer:
without batchNormalizationLayer:
so why?

Answers (0)

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by