Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "de7ccbc2ea2593e65f52ddc8dced0cc01edd3d33"
Commit 123d42e5 authored by chenshi3's avatar chenshi3
Browse files

Update checkpoints of TransFusion and BEVFusion

parent 7cc9e076
Show whitespace changes
Inline Side-by-side
Showing with 7 additions and 6 deletions
README.md
View file @ 123d42e5
...@@ -213,9 +213,10 @@ All models are trained with 8 GPUs and are available for download. For training ...@@ -213,9 +213,10 @@ All models are trained with 8 GPUs and are available for download. For training
| [CenterPoint (voxel_size=0.1)](tools/cfgs/nuscenes_models/cbgs_voxel01_res3d_centerpoint.yaml) | 30.11 | 25.55 | 38.28 | 21.94 | 18.87 | 56.03 | 64.54 | [model-34M](https://drive.google.com/file/d/1Cz-J1c3dw7JAWc25KRG1XQj8yCaOlexQ/view?usp=sharing) | | [CenterPoint (voxel_size=0.1)](tools/cfgs/nuscenes_models/cbgs_voxel01_res3d_centerpoint.yaml) | 30.11 | 25.55 | 38.28 | 21.94 | 18.87 | 56.03 | 64.54 | [model-34M](https://drive.google.com/file/d/1Cz-J1c3dw7JAWc25KRG1XQj8yCaOlexQ/view?usp=sharing) |
| [CenterPoint (voxel_size=0.075)](tools/cfgs/nuscenes_models/cbgs_voxel0075_res3d_centerpoint.yaml) | 28.80 | 25.43 | 37.27 | 21.55 | 18.24 | 59.22 | 66.48 | [model-34M](https://drive.google.com/file/d/1XOHAWm1MPkCKr1gqmc3TWi5AYZgPsgxU/view?usp=sharing) | | [CenterPoint (voxel_size=0.075)](tools/cfgs/nuscenes_models/cbgs_voxel0075_res3d_centerpoint.yaml) | 28.80 | 25.43 | 37.27 | 21.55 | 18.24 | 59.22 | 66.48 | [model-34M](https://drive.google.com/file/d/1XOHAWm1MPkCKr1gqmc3TWi5AYZgPsgxU/view?usp=sharing) |
| [VoxelNeXt (voxel_size=0.075)](tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml) | 30.11 | 25.23 | 40.57 | 21.69 | 18.56 | 60.53 | 66.65 | [model-31M](https://drive.google.com/file/d/1IV7e7G9X-61KXSjMGtQo579pzDNbhwvf/view?usp=share_link) | | [VoxelNeXt (voxel_size=0.075)](tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml) | 30.11 | 25.23 | 40.57 | 21.69 | 18.56 | 60.53 | 66.65 | [model-31M](https://drive.google.com/file/d/1IV7e7G9X-61KXSjMGtQo579pzDNbhwvf/view?usp=share_link) |
| [TransFusion-L](tools/cfgs/nuscenes_models/cbgs_transfusion_lidar.yaml) | 27.96 | 25.37 | 29.35 | 27.31 | 18.55 | 64.58 | 69.43 | [model-32M] | | [TransFusion-L*](tools/cfgs/nuscenes_models/cbgs_transfusion_lidar.yaml) | 27.96 | 25.37 | 29.35 | 27.31 | 18.55 | 64.58 | 69.43 | [model-32M](https://drive.google.com/file/d/1cuZ2qdDnxSwTCsiXWwbqCGF-uoazTXbz/view?usp=share_link) |
| [BEVFusion](tools/cfgs/nuscenes_models/cbgs_bevfusion.yaml) | 28.03 | 25.43 | 30.19 | 26.76 | 18.48 | 67.75 | 70.98 | [model-157M] | | [BEVFusion](tools/cfgs/nuscenes_models/cbgs_bevfusion.yaml) | 28.03 | 25.43 | 30.19 | 26.76 | 18.48 | 67.75 | 70.98 | [model-157M](https://drive.google.com/file/d/1X50b-8immqlqD8VPAUkSKI0Ls-4k37g9/view?usp=share_link) |
*: Use the fade strategy, which disables data augmentations in the last several epochs during training.
### ONCE 3D Object Detection Baselines ### ONCE 3D Object Detection Baselines
All models are trained with 8 GPUs. All models are trained with 8 GPUs.
......
docs/guidelines_of_approaches/bevfusion.md
View file @ 123d42e5
...@@ -13,12 +13,12 @@ Please refer to [GETTING_STARTED.md](../GETTING_STARTED.md) to process the multi ...@@ -13,12 +13,12 @@ Please refer to [GETTING_STARTED.md](../GETTING_STARTED.md) to process the multi
```shell ```shell
bash scripts/dist_train.sh ${NUM_GPUS} --cfg_file cfgs/nuscenes_models/cbgs_transfusion_lidar.yaml \ bash scripts/dist_train.sh ${NUM_GPUS} --cfg_file cfgs/nuscenes_models/cbgs_transfusion_lidar.yaml \
``` ```
The ckpt will be saved in ../output/nuscenes_models/cbgs_transfusion_lidar/default/ckpt. The ckpt will be saved in ../output/nuscenes_models/cbgs_transfusion_lidar/default/ckpt, or you can download pretrained checkpoint directly form [here](https://drive.google.com/file/d/1cuZ2qdDnxSwTCsiXWwbqCGF-uoazTXbz/view?usp=share_link).
1. To train BEVFusion, you need to download pretrained parameters for image backbone [here](www.google.com), and specify the path in [config](../../tools/cfgs/nuscenes_models/cbgs_bevfusion.yaml#L88). Then run the following command: 1. To train BEVFusion, you need to download pretrained parameters for image backbone [here](www.google.com), and specify the path in [config](../../tools/cfgs/nuscenes_models/cbgs_bevfusion.yaml#L88). Then run the following command:
```shell ```shell
bash scripts/dist_train.sh ${NUM_GPUS} --cfg_file cfgs/nuscenes_models/cbgs_bevfusion.yaml \ bash scripts/dist_train.sh ${NUM_GPUS} --cfg_file cfgs/nuscenes_models/cbgs_bevfusion.yaml \
--pretrained_model ../output/nuscenes_models/cbgs_transfusion_lidar/default/ckpt/checkpoint_epoch_20.pth \ --pretrained_model path_to_pretrained_lidar_branch_ckpt \
``` ```
## Evaluation ## Evaluation
* Test with a pretrained model: * Test with a pretrained model:
...@@ -31,5 +31,5 @@ bash scripts/dist_test.sh ${NUM_GPUS} --cfg_file cfgs/nuscenes_models/cbgs_bevf ...@@ -31,5 +31,5 @@ bash scripts/dist_test.sh ${NUM_GPUS} --cfg_file cfgs/nuscenes_models/cbgs_bevf
All models are trained with spconv 1.0, but you can directly load them for testing regardless of the spconv version. All models are trained with spconv 1.0, but you can directly load them for testing regardless of the spconv version.
| | mATE | mASE | mAOE | mAVE | mAAE | mAP | NDS | download | | | mATE | mASE | mAOE | mAVE | mAAE | mAP | NDS | download |
|----------------------------------------------------------------------------------------------------|-------:|:------:|:------:|:-----:|:-----:|:-----:|:------:|:--------------------------------------------------------------------------------------------------:| |----------------------------------------------------------------------------------------------------|-------:|:------:|:------:|:-----:|:-----:|:-----:|:------:|:--------------------------------------------------------------------------------------------------:|
| [TransFusion-L](../../tools/cfgs/nuscenes_models/cbgs_transfusion_lidar.yaml) | 27.96 | 25.37 | 29.35 | 27.31 | 18.55 | 64.58 | 69.43 | [model-32M] | | [TransFusion-L](../../tools/cfgs/nuscenes_models/cbgs_transfusion_lidar.yaml) | 27.96 | 25.37 | 29.35 | 27.31 | 18.55 | 64.58 | 69.43 | [model-32M](https://drive.google.com/file/d/1cuZ2qdDnxSwTCsiXWwbqCGF-uoazTXbz/view?usp=share_link) |
| [BEVFusion](../../tools/cfgs/nuscenes_models/cbgs_bevfusion.yaml) | 28.03 | 25.43 | 30.19 | 26.76 | 18.48 | 67.75 | 70.98 | [model-157M] | | [BEVFusion](../../tools/cfgs/nuscenes_models/cbgs_bevfusion.yaml) | 28.03 | 25.43 | 30.19 | 26.76 | 18.48 | 67.75 | 70.98 | [model-157M](https://drive.google.com/file/d/1X50b-8immqlqD8VPAUkSKI0Ls-4k37g9/view?usp=share_link) |
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment