search

DinoMan / speech-driven-animation

949 stars 289 forks source link

problem: torch.load & pickle. help!!! #51

Open ixNeo opened 4 years ago

ixNeo commented 4 years ago

Traceback (most recent call last): File "/Users/coolinear/Desktop/pyproj/speech-driven-animation-master/mess.py", line 2, in va = sda.VideoAnimator(gpu=-1)# Instantiate the animator File "/Users/coolinear/Desktop/pyproj/speech-driven-animation-master/sda/sda.py", line 106, in init model_dict = torch.load(model_path, map_location=lambda storage, loc: storage) File "/Users/coolinear/anaconda3/lib/python3.7/site-packages/torch/serialization.py", line 426, in load return _load(f, map_location, pickle_module, pickle_load_args) File "/Users/coolinear/anaconda3/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load magic_number = pickle_module.load(f, pickle_load_args) _pickle.UnpicklingError: invalid load key, 'v'.

YTMartian commented 4 years ago

download model from README, here: https://drive.google.com/open?id=1pJdsnknLmMLvA8RQIAV3AQH8vU0FeK16

A-q-p-W commented 3 years ago

download model from README, here: https://drive.google.com/open?id=1pJdsnknLmMLvA8RQIAV3AQH8vU0FeK16

And make sure you put the models in the sda\data folder where there are existing empty placeholder .dat files.

NelsonScott commented 1 year ago

Think the new location is here https://drive.google.com/drive/folders/17Dc2keVoNSrlrOdLL3kXdM8wjb20zkbF