Does batchNormalizationLayer influence network results?
조회 수: 2 (최근 30일)
이전 댓글 표시
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:
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/534384/image.png)
without batchNormalizationLayer:
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/534389/image.png)
so why?
댓글 수: 0
답변 (0개)
참고 항목
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!