Sumai
> Was able to resolve this issue by changing the line to (removed `.module`): > `self.network.load_state_dict(torch.load(self.opt.reload_model_path, map_location='cuda:0'))` > > However, this made it incompatible with the downloaded models in `training/trained_models/`...
i solved this Problem already，i think it;s because the mismatch between save and load model change the 'reload_network' in trainner_model.py line 33 def reload_network(self): """ Reload entire model or only...
change the S1 value in .sh and type on the web browser manually, i can't download with .sh too
> Hi @4ssass1n0r , > I am sorry, I don't understand what you mean. Can you add some context please? > Best regards > Hi @4ssass1n0r , > I am...
> > Hi @4ssass1n0r , > > I am sorry, I don't understand what you mean. Can you add some context please? > > Best regards > > > Hi...