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: Res2Net
- Metadata:
- Training Data: COCO
- Training Techniques:
- - SGD with Momentum
- - Weight Decay
- Training Resources: 8x V100 GPUs
- Architecture:
- - Res2Net
- Paper:
- URL: https://arxiv.org/abs/1904.01169
- Title: 'Res2Net for object detection and instance segmentation'
- README: configs/res2net/README.md
- Code:
- URL: https://github.com/open-mmlab/mmdetection/blob/v2.1.0/mmdet/models/backbones/res2net.py#L239
- Version: v2.1.0
-
- Models:
- - Name: faster_rcnn_r2_101_fpn_2x_coco
- In Collection: Res2Net
- Config: configs/res2net/faster_rcnn_r2_101_fpn_2x_coco.py
- Metadata:
- Training Memory (GB): 7.4
- Epochs: 24
- Results:
- - Task: Object Detection
- Dataset: COCO
- Metrics:
- box AP: 43.0
- Weights: https://download.openmmlab.com/mmdetection/v2.0/res2net/faster_rcnn_r2_101_fpn_2x_coco/faster_rcnn_r2_101_fpn_2x_coco-175f1da6.pth
-
- - Name: mask_rcnn_r2_101_fpn_2x_coco
- In Collection: Res2Net
- Config: configs/res2net/mask_rcnn_r2_101_fpn_2x_coco.py
- Metadata:
- Training Memory (GB): 7.9
- Epochs: 24
- Results:
- - Task: Object Detection
- Dataset: COCO
- Metrics:
- box AP: 43.6
- - Task: Instance Segmentation
- Dataset: COCO
- Metrics:
- mask AP: 38.7
- Weights: https://download.openmmlab.com/mmdetection/v2.0/res2net/mask_rcnn_r2_101_fpn_2x_coco/mask_rcnn_r2_101_fpn_2x_coco-17f061e8.pth
-
- - Name: cascade_rcnn_r2_101_fpn_20e_coco
- In Collection: Res2Net
- Config: configs/res2net/cascade_rcnn_r2_101_fpn_20e_coco.py
- Metadata:
- Training Memory (GB): 7.8
- Epochs: 20
- Results:
- - Task: Object Detection
- Dataset: COCO
- Metrics:
- box AP: 45.7
- Weights: https://download.openmmlab.com/mmdetection/v2.0/res2net/cascade_rcnn_r2_101_fpn_20e_coco/cascade_rcnn_r2_101_fpn_20e_coco-f4b7b7db.pth
-
- - Name: cascade_mask_rcnn_r2_101_fpn_20e_coco
- In Collection: Res2Net
- Config: configs/res2net/cascade_mask_rcnn_r2_101_fpn_20e_coco.py
- Metadata:
- Training Memory (GB): 9.5
- Epochs: 20
- Results:
- - Task: Object Detection
- Dataset: COCO
- Metrics:
- box AP: 46.4
- - Task: Instance Segmentation
- Dataset: COCO
- Metrics:
- mask AP: 40.0
- Weights: https://download.openmmlab.com/mmdetection/v2.0/res2net/cascade_mask_rcnn_r2_101_fpn_20e_coco/cascade_mask_rcnn_r2_101_fpn_20e_coco-8a7b41e1.pth
-
- - Name: htc_r2_101_fpn_20e_coco
- In Collection: Res2Net
- Config: configs/res2net/htc_r2_101_fpn_20e_coco.py
- Metadata:
- Epochs: 20
- Results:
- - Task: Object Detection
- Dataset: COCO
- Metrics:
- box AP: 47.5
- - Task: Instance Segmentation
- Dataset: COCO
- Metrics:
- mask AP: 41.6
- Weights: https://download.openmmlab.com/mmdetection/v2.0/res2net/htc_r2_101_fpn_20e_coco/htc_r2_101_fpn_20e_coco-3a8d2112.pth
|