search

Turoad / CLRNet

Pytorch implementation of our paper "CLRNet: Cross Layer Refinement Network for Lane Detection" (CVPR2022 Acceptance).
Apache License 2.0
479 stars 104 forks source link

OSError: CUDA_HOME environment variable is not set. Please set it to your CUDA install root. #66

Open Miaoishappening opened 1 year ago

Miaoishappening commented 1 year ago

Hi everyone,

I am trying to install some python packages with python setup.py build develop , but i do not have a GPU. so i installed pytorch with “conda install pytorch torchvision torchaudio cpuonly -c pytorch”.

Can i still try this CLRnet or a GPU is a necessary condition in your codes?

YatesZhang commented 1 year ago

NVIDIA GPU is necessary because NMS function is implemented in CUDA. You can overwrite the NMS function in Python, if you insist.

Miaoishappening commented 1 year ago

@YatesZhang Thanks for replying. it helps a lot!

caolong-whu commented 1 year ago

@YatesZhang Thanks for replying. it helps a lot!

Hello！Could you please tell how to solve the problem？I met with the same problem，but I don't know how to overwrite the NMS function。Thanks a lot！

anitach2003 commented 1 year ago

NVIDIA GPU is necessary because NMS function is implemented in CUDA. You can overwrite the NMS function in Python, if you insist.

Hi would you mind tell me what should I do step by step I found these 2 source https://towardsdatascience.com/non-maxima-suppression-139f7e00f0b5 https://github.com/satheeshkatipomu/nms-python and after I overwrite nms what shoud I do?