extractor.train()?

[yunsangq]

Hi, Thanks for your code!!

extractor was not included in the optimizer parameter.
So, I think the extractor was only used for inference, but wonder why used train().
In this case, batch_norm different results than eval().
because running_mean, running_var changed when train().

DFR/DFR-source/anoseg_dfr.py

Line 148 in 5307795

self.extractor.train()

DFR/DFR-source/anoseg_dfr.py

Line 207 in 5307795

self.extractor.train()

DFR/DFR-source/anoseg_dfr.py

Line 78 in 5307795

self.optimizer = optim.Adam(self.autoencoder.parameters(), lr=self.lr, weight_decay=0)