Closed giorgiop closed 2 years ago
I left them out because the library should work with most versions of the dependencies. Some people can use the models as feature extractors so I wanted them to be able to use whatever version they wanted. Is something dependency not working for you?
Hello! I download your code, run the pip install .
I successfully installed all dependence, but when I run the Example with Image and Audio Paths, I got some error like this:
Traceback (most recent call last):
File "d:/Program1/python/ai/sda/speech-driven-animation-master/test.py", line 2, in <module>
va = sda.VideoAnimator(gpu=0, model_path="crema")# Instantiate the animator
File "d:\Program1\python\ai\sda\speech-driven-animation-master\sda\sda.py", line 109, in __init__
model_dict = torch.load(model_path, map_location=lambda storage, loc: storage.cuda(gpu))
File "C:\Users\freest0ne\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\serialization.py", line 713, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "C:\Users\freest0ne\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\serialization.py", line 920, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, 'v'.
should i run this in linux?
Sorry, I forgot to replace files in data, it's has fixed
Yes I have only tested the code on linux so I don't know if there are any issues on windows.
Can you please provide the version of each dependency in
setup.py
?