我的机器是RTX3090,CUDA11.1
1.创建虚拟环境
conda create -n bevfusion python=3.8.3
2.安装PyTorch 和 torchvision
pip install torch==1.8.0+cu111 torchvision==0.9.0+cu111 torchaudio==0.8.0 -f .html
3.安装MMCV
cu111
改了就行pip install mmcv_full-1.4.0-cp38-cp38-manylinux1_x86_64.whl
pip install -U openmim -i
mim install mmcv-full==1.6.0 -i
4.安装mmdet
在代码中mmdetection-2.11.0文件中编译安装,不需要去下载了
cd mmdetection-2.11.0
pip install -r
pip install -v -e .
error: legacy-install-failure× Encountered error while trying to install package.
╰─> mmpycocotools
说明安装pip install -r
时安装的Cython版本太高了,降低版本即可:pip install Cython==0.29.36
,然后再次pip install -v -e .
5.安装MMDetection3D
先回到BEVFusion主目录
cd ..
git clone .git
cd mmdetection3d
pip install -v -e .
6.编译BEVFusion环境
cd ..
python setup.py develop
bug1:
Installed /home/ywj/work/anaconda3/envs/bevfusion/lib/python3.8/site-packages/networkx-2.
error: networkx 2.2 is installed but networkx>=2.8 is required by {'scikit-image'}
pip install scikit-image==0.19.3
Installed /home/ywj/work/anaconda3/envs/bevfusion/lib/python3.8/site-packages/llvmlite-0.31.0-py3.
error: numpy 1.19.5 is installed but numpy>=1.20.3; python_version < "3.10" is required by {'pandas'}
pip install pandas==1.4.4
RuntimeError: radix_sort: failed on 1st step: cudaErrorInvalidDevice: invalid device ordinal(BEVFusion)
原因:torch版本不对
解决办法:显卡是3090,最后安装的是python==3.7,pytorch=1.9.0,cuda=11.1
python tools/create_data.py nuscenes --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag nuscenes
可能出现bug :说明MMCV版本没装对,装的是cuda10.1的版本,重新安装
ImportError: libcudart.so.10.1: cannot open shared object file: No such file or directory
python -u tools/dataset_converters/nuimage_converter.py --data-root /home/ywj/work/data/unimages --version v1.0-train v1.0-val v1.0-mini --out-dir /home/ywj/work/data/unimages/annotations/ --nproc 16
attribute {"token": <str> -- Unique record identifier."name": <str> -- Attribute name."description": <str> -- Attribute description.
}
calibrated_sensor {"token": <str> -- Unique record identifier."sensor_token": <str> -- Foreign key pointing to the sensor type."translation": <float> [3] -- Coordinate system origin in meters: x, y, z."rotation": <float> [4] -- Coordinate system orientation as quaternion: w, x, y, z."camera_intrinsic": <float> [3, 3] -- Intrinsic camera calibration. Empty for sensors that are not cameras."camera_distortion": <float> [5 or 6] -- Camera calibration parameters [k1, k2, p1, p2, k3, k4]. We use the 5 parameter camera convention of the CalTech camera calibration toolbox, that is also used in OpenCV. Only for fish-eye lenses in CAM_BACK do we use the 6th parameter (k4).
}
类别与 nuScenes 中的类别相同(不包含 litarseg),再加上flat.driveable_surface.
category {"token": <str> -- Unique record identifier."name": <str> -- Category name. Subcategories indicated by period."description": <str> -- Category description.
}
本文发布于:2024-02-04 09:14:07,感谢您对本站的认可!
本文链接:https://www.4u4v.net/it/170703858854280.html
版权声明:本站内容均来自互联网,仅供演示用,请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系,我们将在24小时内删除。
留言与评论(共有 0 条评论) |