Checkpoint not working with batch normalization
34 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
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.
0 Kommentare
Antworten (1)
Mahesh Taparia
am 13 Jul. 2020
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 Kommentare
Gelin Guo
am 20 Apr. 2022
Bearbeitet: Gelin Guo
am 20 Apr. 2022
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
am 15 Dez. 2022
For anyone else stuck, there is a fix here: https://uk.mathworks.com/matlabcentral/answers/423588-how-to-classify-with-dag-network-from-checkpoint
Siehe auch
Kategorien
Mehr zu Image Data Workflows finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!