scfive
Resolve README.md conflict and continue rebase
e8f2571
raw
history blame contribute delete
1.63 kB
Collections:
- Name: CrowdDet
Metadata:
Training Data: CrowdHuman
Training Techniques:
- SGD
- EMD Loss
Training Resources: 8x A100 GPUs
Architecture:
- FPN
- RPN
- ResNet
- RoIPool
Paper:
URL: https://arxiv.org/abs/2003.09163
Title: 'Detection in Crowded Scenes: One Proposal, Multiple Predictions'
README: configs/crowddet/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection/blob/v3.0.0rc3/mmdet/models/detectors/crowddet.py
Version: v3.0.0rc3
Models:
- Name: crowddet-rcnn_refine_r50_fpn_8xb2-30e_crowdhuman
In Collection: CrowdDet
Config: configs/crowddet/crowddet-rcnn_refine_r50_fpn_8xb2-30e_crowdhuman.py
Metadata:
Training Memory (GB): 4.8
Epochs: 30
Results:
- Task: Object Detection
Dataset: CrowdHuman
Metrics:
box AP: 90.32
Weights: https://download.openmmlab.com/mmdetection/v3.0/crowddet/crowddet-rcnn_refine_r50_fpn_8xb2-30e_crowdhuman/crowddet-rcnn_refine_r50_fpn_8xb2-30e_crowdhuman_20221024_215917-45602806.pth
- Name: crowddet-rcnn_r50_fpn_8xb2-30e_crowdhuman
In Collection: CrowdDet
Config: configs/crowddet/crowddet-rcnn_r50_fpn_8xb2-30e_crowdhuman.py
Metadata:
Training Memory (GB): 4.4
Epochs: 30
Results:
- Task: Object Detection
Dataset: CrowdHuman
Metrics:
box AP: 90.0
Weights: https://download.openmmlab.com/mmdetection/v3.0/crowddet/crowddet-rcnn_r50_fpn_8xb2-30e_crowdhuman/crowddet-rcnn_r50_fpn_8xb2-30e_crowdhuman_20221023_174954-dc319c2d.pth