【DeepInteraction复现】DeepInteraction: 3D Object Detection via Modality Interaction

原始论文：https://arxiv.org/abs/2208.11112
代码：https://github.com/fudan-zvg/DeepInteraction
我的环境：
系统：Ubuntu20.04
显卡：RTX 3090 24G X2
CPU：13th Gen Intel® Core™ i9-13900K

一、环境配置

依据 install.md

conda create -n deepint python==3.7
conda install pytorch==1.9.1 torchvision==0.10.1 torchaudio==0.9.1 cudatoolkit=11.3 -c pytorch -c conda-forge
# mmlab套件前置
pip install mmcv-full==1.3.18
pip install mmdet==2.14.0
pip install mmsegmentation==0.14.1
# mmdetection3d框架
git clone https://github.com/open-mmlab/mmdetection3d.git
cd mmdetection3d
git checkout v0.17.1
python setup.py install
# detectron2框架
python -m pip install detectron2 -f \
  https://dl.fbaipublicfiles.com/detectron2/wheels/cu111/torch1.9/index.html
# DeepInteraction源码
  git clone https://github.com/fudan-zvg/DeepInteraction.git
cd DeepInteraction

二、数据准备

python tools/create_data.py nuscenes --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag nuscenes

三、训练和测试

# train with 8 GPUs
tools/dist_train.sh projects/configs/nuscenes/Fusion_0075_refactor.py 8
# test with 8 GPUs
tools/dist_test.sh projects/configs/nuscenes/Fusion_0075_refactor.py ${CHECKPOINT_FILE} 8 --eval=bbox

我遇到的问题：