How to save a convnet checkpoint with batchNormalizationLayer

3 ビュー (過去 30 日間)
Zhaoxi Zhang
Zhaoxi Zhang 2017 年 11 月 1 日
I found trainMean and trainVariance of the batchnormalizationLayer are both empty for convnet_checkpoints saved using trainNet and trainOption('CheckpointPath', 'somepath'). This brings the problem that when I try to calculated validation error from a saved checkpoint, it will give the error saying the network is not trained.
Is there some way to set the trainOption so that trainMean and trainVariance will be saved?

サインインしてこの質問に回答する。

回答 (0 件)

カテゴリ

Help Center および File Exchange で Deep Learning Toolbox についてさらに検索

タグ

Community Treasure Hunt

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

Start Hunting!

Translated by