Closed Wallong closed 9 months ago
the same bug,waiting for a solution
same error...
Firstly, thanks for your valuable work. I met the same error, my Pytorch version:2.0.1, Python version:3.9.0, Cuda version: 11.7, Tinycudann version: 1.7, GPU:3090. Is the incompatibility problem? Hope you can help us fix it, thanks a lot. Besides, how can I assign a specific GPU to run the task?
Firstly, thanks for your valuable work. I met the same error, my Pytorch version:2.0.1, Python version:3.9.0, Cuda version: 11.7, Tinycudann version: 1.7, GPU:3090. Is the incompatibility problem? Hope you can help us fix it, thanks a lot. Besides, how can I assign a specific GPU to run the task?
It seems caused by the incompatibility of Tinycudann with Cuda runtime version. It works for me with Python:3.9.0, Pytorch:1.13.1, Cuda:11.7, Tinycudann:1.7. Hope it can help you fix the errors.
closed as solved
Firstly, thanks for your valuable work. I met the same error, my Pytorch version:2.0.1, Python version:3.9.0, Cuda version: 11.7, Tinycudann version: 1.7, GPU:3090. Is the incompatibility problem? Hope you can help us fix it, thanks a lot. Besides, how can I assign a specific GPU to run the task?
It seems caused by the incompatibility of Tinycudann with Cuda runtime version. It works for me with Python:3.9.0, Pytorch:1.13.1, Cuda:11.7, Tinycudann:1.7. Hope it can help you fix the errors.
I've encountered the following problem. Is it because of the version of tinycudann? My version is the same as yours. Did your code run successfully?
# Parameters for TriMipRF:
# ==============================================================================
TriMipRF.feature_dim = 16
TriMipRF.geo_feat_dim = 15
TriMipRF.n_levels = 8
TriMipRF.net_depth_base = 2
TriMipRF.net_depth_color = 4
TriMipRF.net_width = 128
TriMipRF.plane_size = 512
# Parameters for TriMipRFModel:
# ==============================================================================
TriMipRFModel.occ_grid_resolution = 128
TriMipRFModel.samples_per_ray = 1024
2024-01-12 14:33:35.438 | INFO | trainer.trainer:fit:106 - ==> Start training ...
NerfAcc: No CUDA toolkit found. NerfAcc will be disabled.
Traceback (most recent call last):
File "/media/yangtongyu/T9/code1/Tri-MipRF-main/main.py", line 99, in <module>
main()
File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/gin/config.py", line 1605, in gin_wrapper
utils.augment_exception_message_and_reraise(e, err_str)
File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/gin/utils.py", line 41, in augment_exception_message_and_reraise
raise proxy.with_traceback(exception.__traceback__) from None
File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/gin/config.py", line 1582, in gin_wrapper
return fn(*new_args, **new_kwargs)
File "/media/yangtongyu/T9/code1/Tri-MipRF-main/main.py", line 56, in main
trainer.fit()
File "/media/yangtongyu/T9/code1/Tri-MipRF-main/trainer/trainer.py", line 113, in fit
self.model.before_iter(step)
File "/media/yangtongyu/T9/code1/Tri-MipRF-main/neural_field/model/trimipRF.py", line 41, in before_iter
self.ray_sampler.every_n_step(
File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/grid.py", line 271, in every_n_step
self._update(
File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/grid.py", line 224, in _update
x = contract_inv(
File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/contraction.py", line 101, in contract_inv
ctype = type.to_cpp_version()
File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/contraction.py", line 62, in to_cpp_version
return _C.ContractionTypeGetter(self.value)
File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/cuda/__init__.py", line 13, in call_cuda
return getattr(_C, name)(*args, **kwargs)
AttributeError: 'NoneType' object has no attribute 'ContractionType'
In call to configurable 'main' (<function main at 0x7fd229f57b80>)
Firstly, thanks for your valuable work. I met the same error, my Pytorch version:2.0.1, Python version:3.9.0, Cuda version: 11.7, Tinycudann version: 1.7, GPU:3090. Is the incompatibility problem? Hope you can help us fix it, thanks a lot. Besides, how can I assign a specific GPU to run the task?
It seems caused by the incompatibility of Tinycudann with Cuda runtime version. It works for me with Python:3.9.0, Pytorch:1.13.1, Cuda:11.7, Tinycudann:1.7. Hope it can help you fix the errors.
I've encountered the following problem. Is it because of the version of tinycudann? My version is the same as yours. Did your code run successfully?
# Parameters for TriMipRF: # ============================================================================== TriMipRF.feature_dim = 16 TriMipRF.geo_feat_dim = 15 TriMipRF.n_levels = 8 TriMipRF.net_depth_base = 2 TriMipRF.net_depth_color = 4 TriMipRF.net_width = 128 TriMipRF.plane_size = 512 # Parameters for TriMipRFModel: # ============================================================================== TriMipRFModel.occ_grid_resolution = 128 TriMipRFModel.samples_per_ray = 1024 2024-01-12 14:33:35.438 | INFO | trainer.trainer:fit:106 - ==> Start training ... NerfAcc: No CUDA toolkit found. NerfAcc will be disabled. Traceback (most recent call last): File "/media/yangtongyu/T9/code1/Tri-MipRF-main/main.py", line 99, in <module> main() File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/gin/config.py", line 1605, in gin_wrapper utils.augment_exception_message_and_reraise(e, err_str) File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/gin/utils.py", line 41, in augment_exception_message_and_reraise raise proxy.with_traceback(exception.__traceback__) from None File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/gin/config.py", line 1582, in gin_wrapper return fn(*new_args, **new_kwargs) File "/media/yangtongyu/T9/code1/Tri-MipRF-main/main.py", line 56, in main trainer.fit() File "/media/yangtongyu/T9/code1/Tri-MipRF-main/trainer/trainer.py", line 113, in fit self.model.before_iter(step) File "/media/yangtongyu/T9/code1/Tri-MipRF-main/neural_field/model/trimipRF.py", line 41, in before_iter self.ray_sampler.every_n_step( File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/grid.py", line 271, in every_n_step self._update( File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/grid.py", line 224, in _update x = contract_inv( File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/contraction.py", line 101, in contract_inv ctype = type.to_cpp_version() File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/contraction.py", line 62, in to_cpp_version return _C.ContractionTypeGetter(self.value) File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/cuda/__init__.py", line 13, in call_cuda return getattr(_C, name)(*args, **kwargs) AttributeError: 'NoneType' object has no attribute 'ContractionType' In call to configurable 'main' (<function main at 0x7fd229f57b80>)
Yes, the above version works in my 3090. Your problem seemingly caused by NerfAcc, perhaps you didn't install Cuda toolkit or didn't add it's path to your system. You can try "nvcc --version" test if it had been added.
Firstly, thanks for your valuable work. I met the same error, my Pytorch version:2.0.1, Python version:3.9.0, Cuda version: 11.7, Tinycudann version: 1.7, GPU:3090. Is the incompatibility problem? Hope you can help us fix it, thanks a lot. Besides, how can I assign a specific GPU to run the task?
It seems caused by the incompatibility of Tinycudann with Cuda runtime version. It works for me with Python:3.9.0, Pytorch:1.13.1, Cuda:11.7, Tinycudann:1.7. Hope it can help you fix the errors.
I've encountered the following problem. Is it because of the version of tinycudann? My version is the same as yours. Did your code run successfully?
# Parameters for TriMipRF: # ============================================================================== TriMipRF.feature_dim = 16 TriMipRF.geo_feat_dim = 15 TriMipRF.n_levels = 8 TriMipRF.net_depth_base = 2 TriMipRF.net_depth_color = 4 TriMipRF.net_width = 128 TriMipRF.plane_size = 512 # Parameters for TriMipRFModel: # ============================================================================== TriMipRFModel.occ_grid_resolution = 128 TriMipRFModel.samples_per_ray = 1024 2024-01-12 14:33:35.438 | INFO | trainer.trainer:fit:106 - ==> Start training ... NerfAcc: No CUDA toolkit found. NerfAcc will be disabled. Traceback (most recent call last): File "/media/yangtongyu/T9/code1/Tri-MipRF-main/main.py", line 99, in <module> main() File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/gin/config.py", line 1605, in gin_wrapper utils.augment_exception_message_and_reraise(e, err_str) File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/gin/utils.py", line 41, in augment_exception_message_and_reraise raise proxy.with_traceback(exception.__traceback__) from None File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/gin/config.py", line 1582, in gin_wrapper return fn(*new_args, **new_kwargs) File "/media/yangtongyu/T9/code1/Tri-MipRF-main/main.py", line 56, in main trainer.fit() File "/media/yangtongyu/T9/code1/Tri-MipRF-main/trainer/trainer.py", line 113, in fit self.model.before_iter(step) File "/media/yangtongyu/T9/code1/Tri-MipRF-main/neural_field/model/trimipRF.py", line 41, in before_iter self.ray_sampler.every_n_step( File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/grid.py", line 271, in every_n_step self._update( File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/grid.py", line 224, in _update x = contract_inv( File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/contraction.py", line 101, in contract_inv ctype = type.to_cpp_version() File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/contraction.py", line 62, in to_cpp_version return _C.ContractionTypeGetter(self.value) File "/home/yangtongyu/software/anaconda3/envs/trimip/lib/python3.9/site-packages/nerfacc/cuda/__init__.py", line 13, in call_cuda return getattr(_C, name)(*args, **kwargs) AttributeError: 'NoneType' object has no attribute 'ContractionType' In call to configurable 'main' (<function main at 0x7fd229f57b80>)
Yes, the above version works in my 3090. Your problem seemingly caused by NerfAcc, perhaps you didn't install Cuda toolkit or didn't add it's path to your system. You can try "nvcc --version" test if it had been added.
Thank you so much for your kind reply! It is because the path of nvcc is not found. My problem solved!
Hi, great work! When I run nerf_synthetic data I get a CUDA error, is there some configuration that I overlooked that is causing the error?