`torch.nn.DataParallel` changes name of parameters

TPGM/DomainNet_ResNet_Exp/main_finetune.py

Line 127 in 82f0eb0

exclude_list=["head.weight","head.bias"]

Hi,
in line

TPGM/DomainNet_ResNet_Exp/main_finetune.py

Line 108 in 82f0eb0

    
           model = torch.nn.DataParallel(model, device_ids=range(torch.cuda.device_count()))

,

will change the name of the parameters from head.bias to module.head.bias. As a result, TPGM parameters will also be learned for final layer's weight and biases? Is this intentional?

Hi,

Thanks for pointing this out. This is not intentional. The head weights are supposed to be excluded from training. Please change to the exclude_list=["module.head.weight", "module.head.bias"] because they are randomly initalized. I will also update it shortly.

Best,