Yufei ccac9cf800 | 2 years ago | |
---|---|---|
.. | ||
README.md | 2 years ago | |
mask_rcnn_r50_caffe_fpn_syncbn-all_rpn-2conv_lsj_100e_coco.py | 2 years ago | |
mask_rcnn_r50_caffe_fpn_syncbn-all_rpn-2conv_lsj_100e_fp16_coco.py | 2 years ago | |
mask_rcnn_r50_caffe_fpn_syncbn-all_rpn-2conv_lsj_400e_coco.py | 2 years ago | |
mask_rcnn_r50_fpn_syncbn-all_rpn-2conv_lsj_50e_coco.py | 2 years ago | |
mask_rcnn_r50_fpn_syncbn-all_rpn-2conv_lsj_100e_coco.py | 2 years ago | |
mask_rcnn_r50_fpn_syncbn-all_rpn-2conv_lsj_100e_fp16_coco.py | 2 years ago |
We train Mask R-CNN with large-scale jittor and longer schedule as strong baselines.
The modifications follow those in Detectron2.
Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
---|---|---|---|---|---|---|---|---|
R-50-FPN | pytorch | 50e | config | model | log | ||||
R-50-FPN | pytorch | 100e | config | model | log | ||||
R-50-FPN | caffe | 100e | 44.7 | 40.4 | config | model | log | ||
R-50-FPN | caffe | 400e | config | model | log |
When using large-scale jittering, there are sometimes empty proposals in the box and mask heads during training.
This requires MMSyncBN that allows empty tensors. Therefore, please use mmcv-full>=1.3.14 to train models supported in this directory.
No Description
Python Markdown Shell other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》