fundamentalvision / BEVFormer

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
https://arxiv.org/abs/2203.17270
Apache License 2.0
3.28k stars 534 forks source link

安装mmcv报错 #189

Open Chenjiayu20220326 opened 1 year ago

Chenjiayu20220326 commented 1 year ago

报错为: C:\Users\PC\AppData\Local\Temp\pip-install-undsgfsx\mmcv-full_7b94ce8390804870b7adc07a2c6321d9\mmcv\ops\csrc\pytorch\cuda\psamask_cuda.cu(5): fatal error C1083: 无法打开包括文件: “THC/THC.h”: No such file or directory psamask_cuda.cu error: command 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.3\bin\nvcc.exe' failed with exit code 2 [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for mmcv-full Running setup.py clean for mmcv-full Failed to build mmcv-full ERROR: Could not build wheels for mmcv-full, which is required to install pyproject.toml-based projects

环境: cuda:11.3 torch:1.11.0

MillionaireChen commented 8 months ago

请问您的问题解决了吗

FrzMtrsprt commented 7 months ago

You didn't choose a valid torch and cuda version combination, so there are no corresponding prebuilt mmcv wheels. Visit the url in the install command after -f, for example https://download.openmmlab.com/mmcv/dist/cu115/torch1.11.0/index.html, to find out if it's a valid combination. You should see links for prebuilt wheels if it's valid, instead of a NoSuchKey error.