3dtest / configs /imvotenet /metafile.yml
giantmonkeyTC
mm2
c2ca15f
raw
history blame
1.64 kB
Collections:
- Name: ImVoteNet
Metadata:
Training Data: SUNRGBD
Training Techniques:
- AdamW
Training Resources: 8x TITAN Xp
Architecture:
- Faster R-CNN
- VoteNet
- Feature Pyramid Network
Paper:
URL: https://arxiv.org/abs/2001.10692
Title: 'ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes'
README: configs/imvotenet/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/models/detectors/imvotenet.py#L56
Version: v0.12.0
Models:
- Name: imvotenet_faster_rcnn_r50_fpn_2x4_sunrgbd-3d-10class
In Collection: ImVoteNet
Config: configs/imvotenet/imvotenet_faster-rcnn-r50_fpn_4xb2_sunrgbd-3d.py
Metadata:
Training Memory (GB): 2.1
Results:
- Task: Object Detection
Dataset: SUNRGBD-2D
Metrics:
AP@0.5: 62.70
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/imvotenet/imvotenet_faster_rcnn_r50_fpn_2x4_sunrgbd-3d-10class/imvotenet_faster_rcnn_r50_fpn_2x4_sunrgbd-3d-10class_20210819_225618-62eba6ce.pth
- Name: imvotenet_stage2_16x8_sunrgbd-3d-10class
In Collection: ImVoteNet
Config: configs/imvotenet/imvotenet_stage2_8xb16_sunrgbd-3d.py
Metadata:
Training Memory (GB): 9.4
Results:
- Task: 3D Object Detection
Dataset: SUNRGBD-3D
Metrics:
AP@0.25: 64.48
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/imvotenet/imvotenet_stage2_16x8_sunrgbd-3d-10class/imvotenet_stage2_16x8_sunrgbd-3d-10class_20210819_192851-1bcd1b97.pth