You can not select more than 25 topics
Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
|
- Collections:
- - Name: Sparse R-CNN
- Metadata:
- Training Data: COCO
- Training Techniques:
- - SGD with Momentum
- - Weight Decay
- Training Resources: 8x V100 GPUs
- Architecture:
- - FPN
- - ResNet
- - Sparse R-CNN
- Paper:
- URL: https://arxiv.org/abs/2011.12450
- Title: 'Sparse R-CNN: End-to-End Object Detection with Learnable Proposals'
- README: configs/sparse_rcnn/README.md
- Code:
- URL: https://github.com/open-mmlab/mmdetection/blob/v2.9.0/mmdet/models/detectors/sparse_rcnn.py#L6
- Version: v2.9.0
-
- Models:
- - Name: sparse_rcnn_r50_fpn_1x_coco
- In Collection: Sparse R-CNN
- Config: configs/sparse_rcnn/sparse_rcnn_r50_fpn_1x_coco.py
- Metadata:
- Epochs: 12
- Results:
- - Task: Object Detection
- Dataset: COCO
- Metrics:
- box AP: 37.9
- Weights: https://download.openmmlab.com/mmdetection/v2.0/sparse_rcnn/sparse_rcnn_r50_fpn_1x_coco/sparse_rcnn_r50_fpn_1x_coco_20201222_214453-dc79b137.pth
-
- - Name: sparse_rcnn_r50_fpn_mstrain_480-800_3x_coco
- In Collection: Sparse R-CNN
- Config: configs/sparse_rcnn/sparse_rcnn_r50_fpn_mstrain_480-800_3x_coco.py
- Metadata:
- Epochs: 36
- Results:
- - Task: Object Detection
- Dataset: COCO
- Metrics:
- box AP: 42.8
- Weights: https://download.openmmlab.com/mmdetection/v2.0/sparse_rcnn/sparse_rcnn_r50_fpn_mstrain_480-800_3x_coco/sparse_rcnn_r50_fpn_mstrain_480-800_3x_coco_20201218_154234-7bc5c054.pth
-
- - Name: sparse_rcnn_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco
- In Collection: Sparse R-CNN
- Config: configs/sparse_rcnn/sparse_rcnn_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py
- Metadata:
- Epochs: 36
- Results:
- - Task: Object Detection
- Dataset: COCO
- Metrics:
- box AP: 45.0
- Weights: https://download.openmmlab.com/mmdetection/v2.0/sparse_rcnn/sparse_rcnn_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco/sparse_rcnn_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco_20201223_024605-9fe92701.pth
-
- - Name: sparse_rcnn_r101_fpn_mstrain_480-800_3x_coco
- In Collection: Sparse R-CNN
- Config: configs/sparse_rcnn/sparse_rcnn_r101_fpn_mstrain_480-800_3x_coco.py
- Metadata:
- Epochs: 36
- Results:
- - Task: Object Detection
- Dataset: COCO
- Metrics:
- box AP: 44.2
- Weights: https://download.openmmlab.com/mmdetection/v2.0/sparse_rcnn/sparse_rcnn_r101_fpn_mstrain_480-800_3x_coco/sparse_rcnn_r101_fpn_mstrain_480-800_3x_coco_20201223_121552-6c46c9d6.pth
-
- - Name: sparse_rcnn_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco
- In Collection: Sparse R-CNN
- Config: configs/sparse_rcnn/sparse_rcnn_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py
- Metadata:
- Epochs: 36
- Results:
- - Task: Object Detection
- Dataset: COCO
- Metrics:
- box AP: 46.2
- Weights: https://download.openmmlab.com/mmdetection/v2.0/sparse_rcnn/sparse_rcnn_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco/sparse_rcnn_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco_20201223_023452-c23c3564.pth
|