mirror of https://github.com/alibaba/EasyCV.git
10 lines
1005 B
Markdown
10 lines
1005 B
Markdown
# Detection3d Model Zoo
|
|
|
|
## BEVFormer
|
|
|
|
Pretrained on [nuScenes](https://www.nuscenes.org/) dataset.
|
|
|
|
| Algorithm | Config | Params<br/> | Train memory<br/>(GB) | NDS | mAP | Download |
|
|
| ---------- | ------------------------------------------------------------ | ------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
|
|
| BEVFormer-base | [bevformer_base_r101_dcn_nuscenes](https://github.com/alibaba/EasyCV/tree/master/configs/detection3d/bevformer/bevformer_base_r101_dcn_nuscenes.py) | 69M | 23.9 | 52.46 | 41.83 | [model](http://pai-vision-data-hz.oss-accelerate.aliyuncs.com/EasyCV/modelzoo/detection3d/bevformer/epoch_24.pth) |
|