This repository is an official implementation of RecurrentBEV. It is built based on MMDetection3D.
| Backbone | Img Size | Pretrain | NDS | mAP | Config | Download |
|---|---|---|---|---|---|---|
| Res50 | 256x704 | ImageNet | 54.9 | 44.5 | config | model |
| Res101 | 512x1408 | ImageNet | 59.9 | 50.9 | config | - |
| Res101 | 512x1408 | NuImages | 61.2 | 52.8 | config | model |
| Backbone | Img Size | Pretrain | NDS | mAP | Config | Download |
|---|---|---|---|---|---|---|
| V2-99 | 640x1600 | DD3D | 65.1 | 57.3 | config | model |
| ConvNeXt-B | 640x1600 | COCO | 65.1 | 57.4 | config | - |
The below table shows end-to-end FPS (Frames Per Second) of RecurrentBEV measured with a single RTX-3090.
| Method | Pytorch-FP32 | TensorRT-FP32 | TensorRT-FP16 | TensorRT-INT8 |
|---|---|---|---|---|
| RecurrentBEV | 25.6 | 46.3 | 129.3 | 234.8 |
| StreamPETR | 26.7 | 53.9 | 134.6 | 167.4 |
Please follow our documentation step by step. If you like our work, please recommend it to your colleagues and friends.
- RecurretBEV code
- Visualization
- Convert to TRT model
- TensorRT inference
We thank these great works and open-source codebases:
If you find RecurrentBEV is useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.