Closed XuankeShi closed 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)
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
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)