why is my final validation accuracy much lower than the validation accuracy during training?

10 ビュー (過去 30 日間)
YA
YA 2020 年 8 月 19 日
回答済み: Raunak Gupta 2020 年 8 月 29 日
my FINAL validation is: 21%, while most of my validation accuracy measurements is ~70. what could be the reason for that?

回答 (1 件)

Raunak Gupta
Raunak Gupta 2020 年 8 月 29 日
Hi,
This can happen due to presence of batchNormalizationlayer in the Layer graph. Since in batch normalization layers the mean and variance of data is calculated for whole training data at the end of the training it can produce different result than that seen in training phase (because there these statistics are calculated for mini batches only). Also, I see there is no increase in the loss in the last iteration which suggest that the model hasn’t changed much (So, this decrease looks only due to the batchNormalizationlayer). This shows that the training data is not shuffled while training and, I think you can train the model for more epochs.
You may set the Shuffle option to ‘every-epoch’ for better distribution of data while training.

カテゴリ

Help Center および File ExchangeImage Data Workflows についてさらに検索

Community Treasure Hunt

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

Start Hunting!

Translated by