Checkpoint not working with batch normalization

3 次查看（过去 30 天）
Alec Digirolamo
Alec Digirolamo 2020-7-8
评论： Sam Leeney 2022-12-15
I am using the Deep Learning Toolbox to build and train a convolutional network. In my network I have batch normalization layers after my convolutional layers. I attempted to save my progress using the CheckpointPath option, but when I loaded my network from a checkpoint via load('checkpoint_name.mat'), using predict(net, XValidation) gave the following error:
"Error using DAGNetwork/calculatePredict>predictBatch (line 157)
Input network must not have batch normalization layers with empty
Mean or Variance properties. To calculate the batch normalization
statistics, use the trainNetwork function.
Error in DAGNetwork/calculatePredict (line 17)
Y = predictBatch( ...
Error in DAGNetwork/predict (line 131)
Y = this.calculatePredict( ...
Error in SeriesNetwork/predict (line 263)
Y = this.UnderlyingDAGNetwork.predict(X, varargin{:});
Error in TestNetworks (line 7)
YPredicted = predict(net, XValidation);"
Does someone know what causes this and/or how to fix it?
Thanks in advance.

请先登录，再回答此问题。

回答（1 个）

Mahesh Taparia
Mahesh Taparia 2020-7-13
Hi
The possible workaround of this problem is to save the weights of the network or the complete workspace after completion of training using save function. While making the inference, load that back to the workspace. Hope it will help!
  2 个评论
Gelin Guo
Gelin Guo 2022-4-20
编辑：Gelin Guo 2022-4-20
Hi,
This is still a standing issue after 2yrs passed in R2022a. Do you have any updates on this issue? Due to this bug, the checkpoint functionality in the trainedNetwork is basically rendered useless when BatchNormalization layer is in use.
Sam Leeney
Sam Leeney 2022-12-15
For anyone else stuck, there is a fix here: https://uk.mathworks.com/matlabcentral/answers/423588-how-to-classify-with-dag-network-from-checkpoint

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

标签

产品


版本

R2020a

Community Treasure Hunt

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

Start Hunting!

Translated by