Convolution Neural Network Checkpoints with Batch Normalization

2 次查看（过去 30 天）

Joseph Rivera 2019-10-15

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/485494-convolution-neural-network-checkpoints-with-batch-normalization

评论： Sam Leeney 2022-12-15

The main problem that I'm addressing is that checkpoints from trainNetwork() are broken if they have Batch Normalization layers. I think this is a known issue.

I was thinking of running trainNetwork() again on each checkpoint for a single epoch on a small subset of my training images with realmin learning rate just to finish the training without affecting the network too much.

The issue i'm having is setting the average image property in the imageInputLayer to be static. I already have the zerocenter mean value for my entire training dataset and that will be overwritten with the stats from the smaller dataset which is read-only. Do i really have to use the same training set of over 1 mil images at a realmin learning rate to make my checkpoints usable?

Is there another approach i should try?

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Sam Leeney 2022-12-15

Infuriating that a product people actually pay for has left a fundamental bug like this unfixed for so long. The checkpoint function is rendered useless. Using MATLAB is becoming more infuriating every day.

请先登录，再进行评论。

请先登录，再回答此问题。