mzp

Me too

Change cuda to cpu is ok

Thank you for answering, I will try, but in this case, there is a question, is the matrix too large, I am afraid it is difficult to execute the program.

OK，thanks for your reply！

I do run according to the jupyter-notebook file and have converted the weights, so there should be a problem with my operating environment? But other tasks, such as image_crossover.py, image_morphing.py,...

Traceback (most recent call last): File "facial_exchange.py", line 167, in main() File "facial_exchange.py", line 37, in main g_all.load_state_dict(torch.load(args.weight_file, map_location=device)) File "D:\Anaconda\lib\site-packages\torch\serialization.py", line 387, in load return _load(f, map_location, pickle_module, **pickle_load_args)...

Ok, I will try again, thanks for your answer

However, the author stated in the original text that it can be inferred at a higher resolution. The resize (512*512) limits this theory. Where is the problem, can you analyze...

ok,thanks for your reply.

Thans for you reply.