when we do python3.8 ProST_example_regi.py
There was a problem of CUDA error: invalid argument: nv_pt[:,:,2] = src - inv_pt[:,:,2] in posevec2mat.py
File "/home/broncus/Projective-Spatial-Transformers-master/src/posevec2mat.py", line 97, in raydist_range
inv_pt[:,:,2] = src - inv_pt[:,:,2]
File "/home/broncus/miniconda3/lib/python3.8/site-packages/torch/_tensor.py", line 32, in wrapped
return f(*args, **kwargs)
File "/home/broncus/miniconda3/lib/python3.8/site-packages/torch/_tensor.py", line 639, in rsub
return _C._VariableFunctions.rsub(self, other)
RuntimeError: CUDA error: invalid argument
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.
we can not do anything for inv_pt ! when we do print(inv_pt),it still have the same error f CUDA error: invalid argument.
when we do python3.8 ProST_example_regi.py There was a problem of CUDA error: invalid argument: nv_pt[:,:,2] = src - inv_pt[:,:,2] in posevec2mat.py File "/home/broncus/Projective-Spatial-Transformers-master/src/posevec2mat.py", line 97, in raydist_range inv_pt[:,:,2] = src - inv_pt[:,:,2] File "/home/broncus/miniconda3/lib/python3.8/site-packages/torch/_tensor.py", line 32, in wrapped return f(*args, **kwargs) File "/home/broncus/miniconda3/lib/python3.8/site-packages/torch/_tensor.py", line 639, in rsub return _C._VariableFunctions.rsub(self, other) RuntimeError: CUDA error: invalid argument 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. we can not do anything for inv_pt ! when we do print(inv_pt),it still have the same error f CUDA error: invalid argument.