wuwenhai
/
bev-project
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update checkpoint links

This commit is contained in:
Zhijian Liu 2023-09-29 15:42:39 -04:00 committed by GitHub
parent 601961a903
commit 531bf67dd5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -47,9 +47,9 @@ Here, BEVFusion only uses a single model without any test time augmentation. BEV
| Model | Modality | mAP | NDS | Checkpoint |
| :------------------: | :------: | :--: | :--: | :---------: |
| [BEVFusion](configs/nuscenes/det/transfusion/secfpn/camera+lidar/swint_v0p075/convfuser.yaml) | C+L | 68.52 | 71.38 | [Link](https://bevfusion.mit.edu/files/pretrained_updated/bevfusion-det.pth) |
| [Camera-Only Baseline](configs/nuscenes/det/centerhead/lssfpn/camera/256x704/swint/default.yaml) | C | 35.56 | 41.21 | [Link](https://bevfusion.mit.edu/files/pretrained_updated/camera-only-det.pth) |
| [LiDAR-Only Baseline](configs/nuscenes/det/transfusion/secfpn/lidar/voxelnet_0p075.yaml) | L | 64.68 | 69.28 | [Link](https://bevfusion.mit.edu/files/pretrained/lidar-only-det.pth) |
| [BEVFusion](configs/nuscenes/det/transfusion/secfpn/camera+lidar/swint_v0p075/convfuser.yaml) | C+L | 68.52 | 71.38 | [Link](https://www.dropbox.com/scl/fi/ulaz9z4wdwtypjhx7xdi3/bevfusion-det.pth?rlkey=ovusfi2rchjub5oafogou255v&dl=1) |
| [Camera-Only Baseline](configs/nuscenes/det/centerhead/lssfpn/camera/256x704/swint/default.yaml) | C | 35.56 | 41.21 | [Link](https://www.dropbox.com/scl/fi/pxfaz1nc07qa2twlatzkz/camera-only-det.pth?rlkey=f5do81fawie0ssbg9uhrm6p30&dl=1) |
| [LiDAR-Only Baseline](configs/nuscenes/det/transfusion/secfpn/lidar/voxelnet_0p075.yaml) | L | 64.68 | 69.28 | [Link](https://www.dropbox.com/scl/fi/b1zvgrg9ucmv0wtx6pari/lidar-only-det.pth?rlkey=fw73bmdh57jxtudw6osloywah&dl=0) |
*Note*: The camera-only object detection baseline is a variant of BEVDet-Tiny with a much heavier view transformer and other differences in hyperparameters. Thanks to our [efficient BEV pooling](mmdet3d/ops/bev_pool) operator, this model runs fast and has higher mAP than BEVDet-Tiny under the same input resolution. Please refer to [BEVDet repo](https://github.com/HuangJunjie2017/BEVDet) for the original BEVDet-Tiny implementation. The LiDAR-only baseline is TransFusion-L.
@ -57,9 +57,9 @@ Here, BEVFusion only uses a single model without any test time augmentation. BEV
| Model | Modality | mIoU | Checkpoint |
| :------------------: | :------: | :--: | :---------: |
| [BEVFusion](configs/nuscenes/seg/fusion-bev256d2-lss.yaml) | C+L | 62.95 | [Link](https://bevfusion.mit.edu/files/pretrained_updated/bevfusion-seg.pth) |
| [Camera-Only Baseline](configs/nuscenes/seg/camera-bev256d2.yaml) | C | 57.09 | [Link](https://bevfusion.mit.edu/files/pretrained_updated/camera-only-seg.pth) |
| [LiDAR-Only Baseline](configs/nuscenes/seg/lidar-centerpoint-bev128.yaml) | L | 48.56 | [Link](https://bevfusion.mit.edu/files/pretrained/lidar-only-seg.pth) |
| [BEVFusion](configs/nuscenes/seg/fusion-bev256d2-lss.yaml) | C+L | 62.95 | [Link](https://www.dropbox.com/scl/fi/8lgd1hkod2a15mwry0fvd/bevfusion-seg.pth?rlkey=2tmgw7mcrlwy9qoqeui63tay9&dl=1) |
| [Camera-Only Baseline](configs/nuscenes/seg/camera-bev256d2.yaml) | C | 57.09 | [Link](https://www.dropbox.com/scl/fi/cwpcu80n0shmwraegi6z4/camera-only-seg.pth?rlkey=l60kdaz19fq3gwocsjk09e60z&dl=1) |
| [LiDAR-Only Baseline](configs/nuscenes/seg/lidar-centerpoint-bev128.yaml) | L | 48.56 | [Link](https://www.dropbox.com/scl/fi/mi3w6uxvytdre9i42r9k7/lidar-only-seg.pth?rlkey=rve7hx80u3en1gfoi7tjucl72&dl=1) |
## Usage