diff --git a/configs/cylinder3d/README.md b/configs/cylinder3d/README.md index 8183d08ef1..366cd4539d 100644 --- a/configs/cylinder3d/README.md +++ b/configs/cylinder3d/README.md @@ -18,9 +18,10 @@ We implement Cylinder3D and provide the result and checkpoints on Semantickitti ### SemanticKITTI -| Method | Lr schd | Mem (GB) | mIOU | Download | -| :--------: | :-----: | :------: | :------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| Cylinder3D | 3x | 10.2 | 63.1±0.5 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/cylinder3d/cylinder3d_4xb4_3x_semantickitti/cylinder3d_4xb4_3x_semantickitti_20230318_191107-822a8c31.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/cylinder3d/cylinder3d_4xb4_3x_semantickitti/cylinder3d_4xb4_3x_semantickitti_20230318_191107.json) | +| Method | Lr schd | Laser-Polar Mix | Mem (GB) | mIoU | Download | +| :-----------------------------------------------------------------: | :-----: | :-------------: | :------: | :------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | +| [Cylinder3D](./cylinder3d_8xb2-laser-polar-mix-3x_semantickitti.py) | 3x | ✗ | 10.2 | 63.1±0.5 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/cylinder3d/cylinder3d_4xb4_3x_semantickitti/cylinder3d_4xb4_3x_semantickitti_20230318_191107-822a8c31.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/cylinder3d/cylinder3d_4xb4_3x_semantickitti/cylinder3d_4xb4_3x_semantickitti_20230318_191107.json) | +| [Cylinder3D](./cylinder3d_8xb2-laser-polar-mix-3x_semantickitti.py) | 3x | ✔ | 12.8 | 67.0 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/cylinder3d/cylinder3d_8xb2-amp-laser-polar-mix-3x_semantickitti_20230425_144950-372cdf69.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/cylinder3d/cylinder3d_8xb2-amp-laser-polar-mix-3x_semantickitti_20230425_144950.log) | Note: We reproduce the performance comparable with its [official repo](https://github.com/xinge008/Cylinder3D). It's slightly lower than the performance (65.9 mIOU) reported in the paper due to the lack of point-wise refinement and shorter training time. diff --git a/configs/cylinder3d/metafile.yml b/configs/cylinder3d/metafile.yml index e8241cbcca..e24e66b800 100644 --- a/configs/cylinder3d/metafile.yml +++ b/configs/cylinder3d/metafile.yml @@ -15,7 +15,7 @@ Collections: Version: v1.1.0 Models: - - Name: + - Name: cylinder3d_4xb4-3x_semantickitti In Collection: Cylinder3D Config: configs/cylinder3d/cylinder3d_4xb4_3x_semantickitti.py Metadata: @@ -25,5 +25,18 @@ Models: - Task: 3D Semantic Segmentation Dataset: SemanticKITTI Metrics: - mIOU: 63.1 - Weights: + mIoU: 63.1 + Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/cylinder3d/cylinder3d_4xb4_3x_semantickitti/cylinder3d_4xb4_3x_semantickitti_20230318_191107-822a8c31.pth + + - Name: cylinder3d_8xb2-laser-polar-mix-3x_semantickitti + In Collection: Cylinder3D + Config: configs/cylinder3d/cylinder3d_8xb2-laser-polar-mix-3x_semantickitti.py + Metadata: + Training Data: SemanticKITTI + Training Memory (GB): 12.8 + Results: + - Task: 3D Semantic Segmentation + Dataset: SemanticKITTI + Metrics: + mIoU: 67.0 + Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/cylinder3d/cylinder3d_4xb4_3x_semantickitti/cylinder3d_4xb4_3x_semantickitti_20230318_191107-822a8c31.pth diff --git a/configs/minkunet/README.md b/configs/minkunet/README.md index 011fc0484c..c889f7c26e 100644 --- a/configs/minkunet/README.md +++ b/configs/minkunet/README.md @@ -14,22 +14,32 @@ In many robotics and VR/AR applications, 3D-videos are readily-available sources ## Introduction -We implement MinkUNet with [TorchSparse](https://github.com/mit-han-lab/torchsparse) backend and provide the result and checkpoints on SemanticKITTI datasets. +We implement MinkUNet with [TorchSparse](https://github.com/mit-han-lab/torchsparse) / [Minkowski Engine](https://github.com/NVIDIA/MinkowskiEngine) / [Spconv](https://github.com/traveller59/spconv) backend and provide the result and checkpoints on SemanticKITTI datasets. ## Results and models ### SemanticKITTI -| Method | Lr schd | Mem (GB) | mIoU | Download | -| :----------: | :-----: | :------: | :--: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| MinkUNet-W16 | 15e | 3.4 | 60.3 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w16_8xb2-15e_semantickitti/minkunet_w16_8xb2-15e_semantickitti_20230309_160737-0d8ec25b.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w16_8xb2-15e_semantickitti/minkunet_w16_8xb2-15e_semantickitti_20230309_160737.log) | -| MinkUNet-W20 | 15e | 3.7 | 61.6 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w20_8xb2-15e_semantickitti/minkunet_w20_8xb2-15e_semantickitti_20230309_160718-c3b92e6e.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w20_8xb2-15e_semantickitti/minkunet_w20_8xb2-15e_semantickitti_20230309_160718.log) | -| MinkUNet-W32 | 15e | 4.9 | 63.1 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w32_8xb2-15e_semantickitti/minkunet_w32_8xb2-15e_semantickitti_20230309_160710-7fa0a6f1.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w32_8xb2-15e_semantickitti/minkunet_w32_8xb2-15e_semantickitti_20230309_160710.log) | +| Method | Backend | Lr schd | Amp | Laser-Polar Mix | Mem (GB) | Training Time (hours) | FPS | mIoU | Download | +| :-------------------------------------------------------------------------------------------: | :--------------: | :-----: | :-: | :-------------: | :------: | :-------------------: | :----: | :--: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | +| [MinkUNet18-W16](./minkunet18_w16_torchsparse_8xb2-amp-15e_semantickitti.py) | torchsparse | 15e | ✔ | ✗ | 3.4 | - | - | 60.3 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w16_8xb2-15e_semantickitti/minkunet_w16_8xb2-15e_semantickitti_20230309_160737-0d8ec25b.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w16_8xb2-15e_semantickitti/minkunet_w16_8xb2-15e_semantickitti_20230309_160737.log) | +| [MinkUNet18-W20](./minkunet18_w20_torchsparse_8xb2-amp-15e_semantickitti.py) | torchsparse | 15e | ✔ | ✗ | 3.7 | - | - | 61.6 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w20_8xb2-15e_semantickitti/minkunet_w20_8xb2-15e_semantickitti_20230309_160718-c3b92e6e.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w20_8xb2-15e_semantickitti/minkunet_w20_8xb2-15e_semantickitti_20230309_160718.log) | +| [MinkUNet18-W32](./minkunet18_w32_torchsparse_8xb2-amp-15e_semantickitti.py) | torchsparse | 15e | ✔ | ✗ | 4.9 | - | - | 63.1 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w32_8xb2-15e_semantickitti/minkunet_w32_8xb2-15e_semantickitti_20230309_160710-7fa0a6f1.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w32_8xb2-15e_semantickitti/minkunet_w32_8xb2-15e_semantickitti_20230309_160710.log) | +| [MinkUNet34-W32](./minkunet34_w32_minkowski_8xb2-laser-polar-mix-3x_semantickitti.py) | minkowski engine | 3x | ✗ | ✔ | 11.5 | 6.5 | 12.2 | 69.2 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_minkowski_8xb2-laser-polar-mix-3x_semantickitti_20230514_202236-839847a8.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_minkowski_8xb2-laser-polar-mix-3x_semantickitti_20230514_202236.log) | +| [MinkUNet34-W32](./minkunet34_w32_spconv_8xb2-amp-laser-polar-mix-3x_semantickitti.py) | spconv | 3x | ✔ | ✔ | 6.7 | 2 | 14.6\* | 68.3 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_spconv_8xb2-amp-laser-polar-mix-3x_semantickitti_20230512_233152-e0698a0f.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_spconv_8xb2-amp-laser-polar-mix-3x_semantickitti_20230512_233152.log) | +| [MinkUNet34-W32](./minkunet34_w32_spconv_8xb2-laser-polar-mix-3x_semantickitti.py) | spconv | 3x | ✗ | ✔ | 10.5 | 6 | 14.5 | 3 | 69.3 | +| [MinkUNet34-W32](./minkunet34_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti.py) | torchsparse | 3x | ✔ | ✔ | 6.6 | 3 | 12.8 | 69.3 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti_20230512_233511-bef6cad0.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti_20230512_233511.log) | +| [MinkUNet34-W32](./minkunet34_w32_torchsparse_8xb2-laser-polar-mix-3x_semantickitti.py) | torchsparse | 3x | ✗ | ✔ | 11.8 | 5.5 | 15.9 | 68.7 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_torchsparse_8xb2-laser-polar-mix-3x_semantickitti_20230512_233601-2b61b0ab.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_torchsparse_8xb2-laser-polar-mix-3x_semantickitti_20230512_233601.log) | +| [MinkUNet34v2-W32](minkunet34v2_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti.py) | torchsparse | 3x | ✔ | ✔ | 8.9 | - | - | 70.3 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34v2_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti_20230510_221853-b14a68b3.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34v2_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti_20230510_221853.log) | **Note:** We follow the implementation in SPVNAS original [repo](https://github.com/mit-han-lab/spvnas) and W16\\W20\\W32 indicates different number of channels. **Note:** Due to TorchSparse backend, the model performance is unstable with TorchSparse backend and may fluctuate by about 1.5 mIoU for different random seeds. +**Note:** Referring to [PCSeg](https://github.com/PJLab-ADG/PCSeg), MinkUNet34v2 is modified based on MinkUNet34. + +**Note\*:** Training Time and FPS are measured on NVIDIA A100. The versions of Torchsparse, Minkowski Engine and Spconv are 0.5.4, 1.4.0 and 2.3.6 respectively. Since spconv 2.3.6 has a bug with fp16 on in the inference stage, the actual FPS measurement using fp32. + ## Citation ```latex diff --git a/configs/minkunet/metafile.yml b/configs/minkunet/metafile.yml index 60d4e637bc..f9ae704cd4 100644 --- a/configs/minkunet/metafile.yml +++ b/configs/minkunet/metafile.yml @@ -14,9 +14,9 @@ Collections: Version: v1.1.0 Models: - - Name: minkunet_w16_8xb2-15e_semantickitti + - Name: minkunet18_w16_torchsparse_8xb2-amp-15e_semantickitti In Collection: MinkUNet - Config: configs/minkunet/minkunet_w16_8xb2-15e_semantickitti.py + Config: configs/minkunet/minkunet18_w16_torchsparse_8xb2-amp-15e_semantickitti.py Metadata: Training Data: SemanticKITTI Training Memory (GB): 3.4 @@ -28,9 +28,9 @@ Models: mIoU: 60.3 Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w16_8xb2-15e_semantickitti/minkunet_w16_8xb2-15e_semantickitti_20230309_160737-0d8ec25b.pth - - Name: minkunet_w20_8xb2-15e_semantickitti + - Name: minkunet18_w20_torchsparse_8xb2-amp-15e_semantickitti In Collection: MinkUNet - Config: configs/minkunet/minkunet_w20_8xb2-15e_semantickitti.py + Config: configs/minkunet/minkunet18_w20_torchsparse_8xb2-amp-15e_semantickitti.py Metadata: Training Data: SemanticKITTI Training Memory (GB): 3.7 @@ -42,9 +42,9 @@ Models: mIoU: 61.6 Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w20_8xb2-15e_semantickitti/minkunet_w20_8xb2-15e_semantickitti_20230309_160718-c3b92e6e.pth - - Name: minkunet_w32_8xb2-15e_semantickitti + - Name: minkunet18_w32_torchsparse_8xb2-amp-15e_semantickitti In Collection: MinkUNet - Config: configs/minkunet/minkunet_w32_8xb2-15e_semantickitti.py + Config: configs/minkunet/minkunet18_w32_torchsparse_8xb2-amp-15e_semantickitti.py Metadata: Training Data: SemanticKITTI Training Memory (GB): 4.9 @@ -55,3 +55,87 @@ Models: Metrics: mIoU: 63.1 Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet_w32_8xb2-15e_semantickitti/minkunet_w32_8xb2-15e_semantickitti_20230309_160710-7fa0a6f1.pth + + - Name: minkunet34_w32_minkowski_8xb2-laser-polar-mix-3x_semantickitti + In Collection: MinkUNet + Config: configs/minkunet/minkunet34_w32_minkowski_8xb2-laser-polar-mix-3x_semantickitti.py + Metadata: + Training Data: SemanticKITTI + Training Memory (GB): 11.5 + Training Resources: 8x A100 GPUs + Results: + - Task: 3D Semantic Segmentation + Dataset: SemanticKITTI + Metrics: + mIoU: 69.2 + Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_minkowski_8xb2-laser-polar-mix-3x_semantickitti_20230514_202236-839847a8.pth + + - Name: minkunet34_w32_spconv_8xb2-amp-laser-polar-mix-3x_semantickitti + In Collection: MinkUNet + Config: configs/minkunet/minkunet34_w32_spconv_8xb2-amp-laser-polar-mix-3x_semantickitti.py + Metadata: + Training Data: SemanticKITTI + Training Memory (GB): 6.7 + Training Resources: 8x A100 GPUs + Results: + - Task: 3D Semantic Segmentation + Dataset: SemanticKITTI + Metrics: + mIoU: 68.3 + Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_spconv_8xb2-amp-laser-polar-mix-3x_semantickitti_20230512_233152-e0698a0f.pth + + - Name: minkunet34_w32_spconv_8xb2-laser-polar-mix-3x_semantickitti + In Collection: MinkUNet + Config: configs/minkunet/minkunet34_w32_spconv_8xb2-laser-polar-mix-3x_semantickitti.py + Metadata: + Training Data: SemanticKITTI + Training Memory (GB): 10.5 + Training Resources: 8x A100 GPUs + Results: + - Task: 3D Semantic Segmentation + Dataset: SemanticKITTI + Metrics: + mIoU: 69.3 + Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_spconv_8xb2-laser-polar-mix-3x_semantickitti_20230512_233817-72b200d8.pth + + - Name: minkunet34_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti + In Collection: MinkUNet + Config: configs/minkunet/minkunet34_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti.py + Metadata: + Training Data: SemanticKITTI + Training Memory (GB): 6.6 + Training Resources: 8x A100 GPUs + Results: + - Task: 3D Semantic Segmentation + Dataset: SemanticKITTI + Metrics: + mIoU: 69.3 + Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti_20230512_233511-bef6cad0.pth + + - Name: minkunet34_w32_torchsparse_8xb2-laser-polar-mix-3x_semantickitti + In Collection: MinkUNet + Config: configs/minkunet/minkunet34_w32_torchsparse_8xb2-laser-polar-mix-3x_semantickitti.py + Metadata: + Training Data: SemanticKITTI + Training Memory (GB): 11.8 + Training Resources: 8x A100 GPUs + Results: + - Task: 3D Semantic Segmentation + Dataset: SemanticKITTI + Metrics: + mIoU: 68.7 + Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34_w32_torchsparse_8xb2-laser-polar-mix-3x_semantickitti_20230512_233601-2b61b0ab.pth + + - Name: minkunet34v2_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti + In Collection: MinkUNet + Config: configs/minkunet/minkunet34v2_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti.py + Metadata: + Training Data: SemanticKITTI + Training Memory (GB): 8.9 + Training Resources: 8x A100 GPUs + Results: + - Task: 3D Semantic Segmentation + Dataset: SemanticKITTI + Metrics: + mIoU: 70.3 + Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/minkunet/minkunet34v2_w32_torchsparse_8xb2-amp-laser-polar-mix-3x_semantickitti_20230510_221853-b14a68b3.pth diff --git a/configs/spvcnn/README.md b/configs/spvcnn/README.md index 4f27c4b680..870e98c2ec 100644 --- a/configs/spvcnn/README.md +++ b/configs/spvcnn/README.md @@ -20,11 +20,12 @@ We implement SPVCNN with [TorchSparse](https://github.com/mit-han-lab/torchspars ### SemanticKITTI -| Method | Lr schd | Mem (GB) | mIoU | Download | -| :--------: | :-----: | :------: | :--: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| SPVCNN-W16 | 15e | 3.9 | 61.8 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w16_8xb2-15e_semantickitti/spvcnn_w16_8xb2-15e_semantickitti_20230321_011645-a2734d85.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w16_8xb2-15e_semantickitti/spvcnn_w16_8xb2-15e_semantickitti_20230321_011645.log) | -| SPVCNN-W20 | 15e | 4.2 | 62.6 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w20_8xb2-15e_semantickitti/spvcnn_w20_8xb2-15e_semantickitti_20230321_011649-519e7eff.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w20_8xb2-15e_semantickitti/spvcnn_w20_8xb2-15e_semantickitti_20230321_011649.log) | -| SPVCNN-W32 | 15e | 5.4 | 64.3 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w32_8xb2-15e_semantickitti/spvcnn_w32_8xb2-15e_semantickitti_20230308_113324-f7c0c5b4.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/pvcnn_w32_8xb2-15e_semantickitti/spvcnn_w32_8xb2-15e_semantickitti_20230308_113324.log) | +| Method | Lr schd | Laser-Polar Mix | Mem (GB) | mIoU | Download | +| :---------------------------------------------------------------------: | :-----: | :-------------: | :------: | :--: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | +| [SPVCNN-W16](./spvcnn_w16_8xb2-amp-15e_semantickitti.py) | 15e | ✗ | 3.9 | 61.8 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w16_8xb2-15e_semantickitti/spvcnn_w16_8xb2-15e_semantickitti_20230321_011645-a2734d85.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w16_8xb2-15e_semantickitti/spvcnn_w16_8xb2-15e_semantickitti_20230321_011645.log) | +| [SPVCNN-W20](./spvcnn_w20_8xb2-amp-15e_semantickitti.py) | 15e | ✗ | 4.2 | 62.6 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w20_8xb2-15e_semantickitti/spvcnn_w20_8xb2-15e_semantickitti_20230321_011649-519e7eff.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w20_8xb2-15e_semantickitti/spvcnn_w20_8xb2-15e_semantickitti_20230321_011649.log) | +| [SPVCNN-W32](./spvcnn_w32_8xb2-amp-15e_semantickitti.py) | 15e | ✗ | 5.4 | 64.3 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w32_8xb2-15e_semantickitti/spvcnn_w32_8xb2-15e_semantickitti_20230308_113324-f7c0c5b4.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w32_8xb2-15e_semantickitti/spvcnn_w32_8xb2-15e_semantickitti_20230308_113324.log) | +| [SPVCNN-W32](./spvcnn_w32_8xb2-amp-laser-polar-mix-3x_semantickitti.py) | 3x | ✔ | 7.2 | 68.7 | [model](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w32_8xb2-amp-laser-polar-mix-3x_semantickitti_20230425_125908-d68a68b7.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w32_8xb2-amp-laser-polar-mix-3x_semantickitti_20230425_125908.log) | **Note:** We follow the implementation in SPVNAS original [repo](https://github.com/mit-han-lab/spvnas) and W16\\W20\\W32 indicates different number of channels. diff --git a/configs/spvcnn/metafile.yml b/configs/spvcnn/metafile.yml index 0f3ce9feff..e3f1cfd891 100644 --- a/configs/spvcnn/metafile.yml +++ b/configs/spvcnn/metafile.yml @@ -14,9 +14,9 @@ Collections: Version: v1.1.0 Models: - - Name: spvcnn_w16_8xb2-15e_semantickitti + - Name: spvcnn_w16_8xb2-amp-15e_semantickitti In Collection: SPVCNN - Config: configs/spvcnn/spvcnn_w16_8xb2-15e_semantickitti.py + Config: configs/spvcnn/spvcnn_w16_8xb2-amp-15e_semantickitti.py Metadata: Training Data: SemanticKITTI Training Memory (GB): 3.9 @@ -28,9 +28,9 @@ Models: mIOU: 61.7 Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w16_8xb2-15e_semantickitti/spvcnn_w16_8xb2-15e_semantickitti_20230321_011645-a2734d85.pth - - Name: spvcnn_w20_8xb2-15e_semantickitti + - Name: spvcnn_w20_8xb2-amp-15e_semantickitti In Collection: SPVCNN - Config: configs/spvcnn/spvcnn_w20_8xb2-15e_semantickitti.py + Config: configs/spvcnn/spvcnn_w20_8xb2-amp-15e_semantickitti.py Metadata: Training Data: SemanticKITTI Training Memory (GB): 4.2 @@ -42,9 +42,9 @@ Models: mIOU: 62.9 Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w20_8xb2-15e_semantickitti/spvcnn_w20_8xb2-15e_semantickitti_20230321_011649-519e7eff.pth - - Name: spvcnn_w32_8xb2-15e_semantickitti + - Name: spvcnn_w32_8xb2-amp-15e_semantickitti In Collection: SPVCNN - Config: configs/spvcnn/spvcnn_w32_8xb2-15e_semantickitti.py + Config: configs/spvcnn/spvcnn_w32_8xb2-amp-15e_semantickitti.py Metadata: Training Data: SemanticKITTI Training Memory (GB): 5.4 @@ -55,3 +55,17 @@ Models: Metrics: mIOU: 64.3 Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w32_8xb2-15e_semantickitti/spvcnn_w32_8xb2-15e_semantickitti_20230308_113324-f7c0c5b4.pth + + - Name: spvcnn_w32_8xb2-amp-laser-polar-mix-3x_semantickitti + In Collection: SPVCNN + Config: configs/spvcnn/spvcnn_w32_8xb2-amp-laser-polar-mix-3x_semantickitti.py + Metadata: + Training Data: SemanticKITTI + Training Memory (GB): 7.2 + Training Resources: 8x A100 GPUs + Results: + - Task: 3D Semantic Segmentation + Dataset: SemanticKITTI + Metrics: + mIOU: 64.3 + Weights: https://download.openmmlab.com/mmdetection3d/v1.1.0_models/spvcnn/spvcnn_w32_8xb2-amp-laser-polar-mix-3x_semantickitti_20230425_125908-d68a68b7.pth