Open SY-Xuan opened 4 years ago
https://github.com/liyiying/Feature_Critic/blob/417eca68168537b7edfe154e3c5a5f3bb1e8947c/utils.py#L24 Sorry, I don't understand the meaning of this function, I hope you could explain it.
And in model_PACS.py line 387-392
temp_new_feature_extractor_network = alexnet(pretrained=False).cuda() fix_nn(temp_new_feature_extractor_network, theta_updated_new) temp_new_feature_extractor_network.train() temp_old_feature_extractor_network = alexnet(pretrained=False).cuda() temp_old_feature_extractor_network.load_state_dict(theta_updated_old) temp_old_feature_extractor_network.train()
Why do you use function fix_nn to generate temp_new_feature_extractor_network but use load_state_dict to generate temp_old_feature_extractor_network?
https://github.com/liyiying/Feature_Critic/blob/417eca68168537b7edfe154e3c5a5f3bb1e8947c/utils.py#L24 Sorry, I don't understand the meaning of this function, I hope you could explain it.
And in model_PACS.py line 387-392
temp_new_feature_extractor_network = alexnet(pretrained=False).cuda() fix_nn(temp_new_feature_extractor_network, theta_updated_new) temp_new_feature_extractor_network.train() temp_old_feature_extractor_network = alexnet(pretrained=False).cuda() temp_old_feature_extractor_network.load_state_dict(theta_updated_old) temp_old_feature_extractor_network.train()Why do you use function fix_nn to generate temp_new_feature_extractor_network but use load_state_dict to generate temp_old_feature_extractor_network?