@@ -34,12 +34,12 @@ State-of-the-art object detection networks depend on region proposal algorithms
3434
3535We trained with R-50-FPN pytorch style backbone for 1x schedule.
3636
37- | Backbone | Loss type | Mem (GB) | Inf time (fps) | box AP | Config | Download |
38- | :------: | :------------: | :------: | :------------: | :----: | :--------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
39- | R-50-FPN | L1Loss | 4.0 | 21.4 | 37.4 | [ config] ( https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py ) | [ model] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth ) \| [ log] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130_204655.log.json ) |
40- | R-50-FPN | IoULoss | | | 37.9 | [ config] ( https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_iou_1x_coco.py ) | [ model] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_iou_1x_coco/faster_rcnn_r50_fpn_iou_1x_coco_20200506_095954-938e81f0.pth ) \| [ log] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_iou_1x_coco/faster_rcnn_r50_fpn_iou_1x_coco_20200506_095954.log.json ) |
41- | R-50-FPN | GIoULoss | | | 37.6 | [ config] ( https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py ) | [ model] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_giou_1x_coco-0eada910.pth ) \| [ log] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_giou_1x_coco_20200505_161120.log.json ) |
42- | R-50-FPN | BoundedIoULoss | | | 37.4 | [ config] ( https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco .py ) | [ model] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_bounded_iou_1x_coco-98ad993b.pth ) \| [ log] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_bounded_iou_1x_coco_20200505_160738.log.json ) |
37+ | Backbone | Loss type | Mem (GB) | Inf time (fps) | box AP | Config | Download |
38+ | :------: | :------------: | :------: | :------------: | :----: | :---------------------------------------------------------------------------------------------------------------------------- : | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
39+ | R-50-FPN | L1Loss | 4.0 | 21.4 | 37.4 | [ config] ( https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py ) | [ model] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth ) \| [ log] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130_204655.log.json ) |
40+ | R-50-FPN | IoULoss | | | 37.9 | [ config] ( https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_iou_1x_coco.py ) | [ model] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_iou_1x_coco/faster_rcnn_r50_fpn_iou_1x_coco_20200506_095954-938e81f0.pth ) \| [ log] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_iou_1x_coco/faster_rcnn_r50_fpn_iou_1x_coco_20200506_095954.log.json ) |
41+ | R-50-FPN | GIoULoss | | | 37.6 | [ config] ( https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py ) | [ model] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_giou_1x_coco-0eada910.pth ) \| [ log] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_giou_1x_coco_20200505_161120.log.json ) |
42+ | R-50-FPN | BoundedIoULoss | | | 37.4 | [ config] ( https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_bounded_iou_1x_coco .py ) | [ model] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_bounded_iou_1x_coco-98ad993b.pth ) \| [ log] ( https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_bounded_iou_1x_coco_20200505_160738.log.json ) |
4343
4444## Pre-trained Models
4545
0 commit comments