JeremyCJM / DiffSHEG

[CVPR'24] DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation
https://jeremycjm.github.io/proj/DiffSHEG/
BSD 3-Clause "New" or "Revised" License
112 stars 9 forks source link

Floating point exception(core dumped) #15

Closed XuankeShi closed 2 months ago

XuankeShi commented 2 months ago

i run the inference code by the command "bash inference_custom_audio_beat.sh" but the code failed in the model forward process model_output = model(x, self._scale_timesteps(t), **model_kwargs)

xungeer29 commented 1 month ago

I also have this problem. How to solve it?

xungeer29 commented 1 month ago

I also have this problem. How to solve it?

找到问题了,是torch版本与numpy版本的问题,先导入numpy,再导入torch,就会发生这种情况 升级torch版本可以解决