Please prepare the training environment according to BEVDet.
training script:
./tools/dist_train.sh configs/fastbev/paper/fastbev-r50-cbgs.py 8test script:
./tools/dist_test.sh configs/fastbev/paper/fastbev-r50-cbgs.py work_dirs/fastbev-r50-cbgs/epoch_20_ema.pth 8 --eval mAP 2>&1 | tee work_dirs/fastbev-r50-cbgs/epoch_20_ema.pth.logExported onnx: Google Drive. Trt Latency based on onnx: Google Drive.
This project is not possible without multiple great open-sourced code bases. We list some notable examples below.
- open-mmlab
- CenterPoint
- Lift-Splat-Shoot
- Swin Transformer
- BEVFusion
- BEVDepth
- BEVerse for multi-task learning.
- BEVStereo for stero depth estimation.
- BEVDet
- Fast-BEV


