【论文复现】BEVFormer

conda create -n open-mmlab python=3.8 -y
conda activate open-mmlab

pip install torch==1.9.1+cu111 torchvision==0.10.1+cu111 torchaudio==0.9.1 -f https://download.pytorch.org/whl/torch_stable.html
# Recommended torch>=1.9

c. Install mmcv-full.

pip install mmcv-full==1.4.0
#  pip install mmcv-full==1.4.0 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.9.0/index.html

pip install mmdet==2.14.0
pip install mmsegmentation==0.14.1

git clone https://github.com/open-mmlab/mmdetection3d.git
cd mmdetection3d
git checkout v0.17.1 # Other versions may not be compatible.
python setup.py install

pip install einops fvcore seaborn iopath==0.1.9 timm==0.6.13  typing-extensions==4.5.0 pylint ipython==8.12  numpy==1.19.5 matplotlib==3.5.2 numba==0.48.0 pandas==1.4.4 scikit-image==0.19.3 setuptools==59.5.0
python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'

git clone https://github.com/fundamentalvision/BEVFormer.git

cd bevformer
mkdir ckpts

cd ckpts & wget https://github.com/zhiqi-li/storage/releases/download/v1.0/r101_dcn_fcos3d_pret

# download 'can_bus.zip'
unzip can_bus.zip 
# move can_bus to data dir

python tools/create_data.py nuscenes --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag nuscenes --version v1.0-mini --canbus ./data

bevformer
├── projects/
├── tools/
├── configs/
├── ckpts/
│   ├── r101_dcn_fcos3d_pretrain.pth
├── data/
│   ├── can_bus/
│   ├── nuscenes/
│   │   ├── maps/
│   │   ├── samples/
│   │   ├── sweeps/
│   │   ├── v1.0-test/
|   |   ├── v1.0-trainval/
|   |   ├── nuscenes_infos_temporal_train.pkl
|   |   ├── nuscenes_infos_temporal_val.pkl

./tools/dist_train.sh ./projects/configs/bevformer/bevformer_base.py 8

./tools/dist_test.sh ./projects/configs/bevformer/bevformer_base.py ./path/to/ckpts.pth 8

./tools/fp16/dist_train.sh ./projects/configs/bevformer_fp16/bevformer_tiny_fp16.py 8

# 错误1
...
    from numba.np.ufunc import _internal
SystemError: initialization of _internal failed without raising an exception
# 修改方法： 降低numpy版本即可
pip install numpy==1.23.4

# 错误2
ModuleNotFoundError: No module named 'spconv'
# 修改方法  需要跟cuda配置上, 本人是cuda-11.3, 安装版本如下
pip install spconv-cu113

# 错误3
ModuleNotFoundError: No module named 'IPython'
# 修改方法
pip install IPython

# 错误4
# 情况1：'No module named 'projects.mmdet3d_plugin'
# 情况2：ModuleNotFoundError: No module named 'tools'
# 情况3: ModuleNotFoundError: No module named 'tools.data_converter'
# 因为tools和projects.mmdet3d_plugin都是从本地导入模块, 
# 导入失败要么是python环境变量没生效, 要么是模块的路径不对
# 修改办法: 更新python-path环境即可, 当前python虚拟环境的终端执行下面语句
export PYTHONPATH=$PYTHONPATH:"./"
# 如果还报错检查这句代码的路径是否正确, 可是使用绝对路径代替

# 错误5
TypeError: FormatCode() got an unexpected keyword argument 'verify'
# 修改办法: 降低yapf版本
pip install yapf==0.40.1

# 错误6 
ImportError: libcudart.so.11.0: cannot open shared object file: No such file or directory
# 原因： 安装的mmcv与cuda版本没对用上，建议去whl官方下载离线安装
# 修改参考1.4.1安装mmcv-full教程

# 错误7
# AttributeError: module 'distutils' has no attribute 'version'
修改：更新setuptools版本
pip install setuptools==58.4.0

# 错误8
# docker里面提示libGL.so.1不存在
ImportError: libGL.so.1: cannot open shared object file: No such file or directory
# 修改方法：安装ffmpeg即可
apt-get install ffmpeg -y

# 错误9 pip安装mmcv-full时报错
subprocess.CalledProcessError: Command '['which', 'g++']' returned non-zero exit status 1.
      [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
# 修改方法：由于g++，gcc工具没安装,安装build-essential即可
sudo apt-get install build-essential

# 错误10 训练时显存爆炸 RuntimeError: CUDA out of memory
# 修改：先将配置文件中samples_per_gpu改为1即可workers_per_gpu改0测试环境，
# 后期正式训练时逐渐增加这2个参数的数字, 直到显存占满
# 如果设置成1和0都显存不够, 可以更换显卡了
samples_per_gpu=1, workers_per_gpu=0 

https://zhuanlan.zhihu.com/p/658855697
@article{li2022bevformer,
  title={BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers},
  author={Li, Zhiqi and Wang, Wenhai and Li, Hongyang and Xie, Enze and Sima, Chonghao and Lu, Tong and Qiao, Yu and Dai, Jifeng}
  journal={arXiv preprint arXiv:2203.17270},
  year={2022}
}
@article{Yang2022BEVFormerVA,
  title={BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision},
  author={Chenyu Yang and Yuntao Chen and Haofei Tian and Chenxin Tao and Xizhou Zhu and Zhaoxiang Zhang and Gao Huang and Hongyang Li and Y. Qiao and Lewei Lu and Jie Zhou and Jifeng Dai},
  journal={ArXiv},
  year={2022},
}