Does batchNormalizationLayer influence network results?

1 vue (au cours des 30 derniers jours)
Jack Xiao
Jack Xiao le 28 Fév 2021
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?

Réponses (0)


En savoir plus sur Deep Learning Toolbox dans Help Center et File Exchange




Community Treasure Hunt

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

Start Hunting!

Translated by