target model optimizer in DA

[chenxi52]

optimizer_T in train_DA.py of 'SHOT' method only optimizes net_T.base.parameters() without net_T.bottleneck ,but function train_net_T() in da_trainer.py sets self.net_T.bottleneck.train() mode. Don't they conflicts with each other?

[hou-yz]

thank you for your question.

no, they do not.

please see pytorch documents for how optimizer and the .train() call work. in short, optimizer updates parameters (please go see the definition of parameters); while the .train() call allows certain stuff like statistics in BN layers (not included in parameters) to be updated, and changes behaviors of certain layers like dropout.

Best,
Yunzhong