I am running a CO Pro + subsciption.
But after the run I received the following error :
What do I need to do to fix this ?
Thank you
Starting Run: TimeToDisco(5) at frame 0
Prepping model...
RuntimeError Traceback (most recent call last)
in ()
161 model, diffusion = create_model_and_diffusion(**model_config)
162 model.load_state_dict(torch.load(f'{model_path}/{diffusion_model}.pt', map_location='cpu'))
--> 163 model.requiresgrad(False).eval().to(device)
164 for name, param in model.named_parameters():
165 if 'qkv' in name or 'norm' in name or 'proj' in name:
4 frames
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in convert(t)
903 return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None,
904 non_blocking, memory_format=convert_to_format)
--> 905 return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
906
907 return self._apply(convert)
RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Hi there,
I am running a CO Pro + subsciption. But after the run I received the following error : What do I need to do to fix this ? Thank you
Starting Run: TimeToDisco(5) at frame 0 Prepping model...
RuntimeError Traceback (most recent call last)()
161 model, diffusion = create_model_and_diffusion(**model_config)
162 model.load_state_dict(torch.load(f'{model_path}/{diffusion_model}.pt', map_location='cpu'))
--> 163 model.requiresgrad(False).eval().to(device)
164 for name, param in model.named_parameters():
165 if 'qkv' in name or 'norm' in name or 'proj' in name:
4 frames /usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in convert(t) 903 return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, 904 non_blocking, memory_format=convert_to_format) --> 905 return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking) 906 907 return self._apply(convert)
RuntimeError: CUDA error: an illegal memory access was encountered CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1.