Yufei ccac9cf800 | 2 years ago | |
---|---|---|
.. | ||
README.md | 2 years ago | |
faster_rcnn_r50_fpg-chn128_crop640_50e_coco.py | 2 years ago | |
faster_rcnn_r50_fpg_crop640_50e_coco.py | 2 years ago | |
faster_rcnn_r50_fpn_crop640_50e_coco.py | 2 years ago | |
mask_rcnn_r50_fpg-chn128_crop640_50e_coco.py | 2 years ago | |
mask_rcnn_r50_fpg_crop640_50e_coco.py | 2 years ago | |
mask_rcnn_r50_fpn_crop640_50e_coco.py | 2 years ago | |
metafile.yml | 2 years ago | |
retinanet_r50_fpg-chn128_crop640_50e_coco.py | 2 years ago | |
retinanet_r50_fpg_crop640_50e_coco.py | 2 years ago |
@article{chen2020feature,
title={Feature pyramid grids},
author={Chen, Kai and Cao, Yuhang and Loy, Chen Change and Lin, Dahua and Feichtenhofer, Christoph},
journal={arXiv preprint arXiv:2004.03580},
year={2020}
}
We benchmark the new training schedule (crop training, large batch, unfrozen BN, 50 epochs) introduced in NAS-FPN.
All backbones are Resnet-50 in pytorch style.
Method | Neck | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
---|---|---|---|---|---|---|---|---|
Faster R-CNN | FPG | 50e | 20.0 | - | 42.2 | - | config | model | log |
Faster R-CNN | FPG-chn128 | 50e | 11.9 | - | 41.2 | - | config | model | log |
Mask R-CNN | FPG | 50e | 23.2 | - | 42.7 | 37.8 | config | model | log |
Mask R-CNN | FPG-chn128 | 50e | 15.3 | - | 41.7 | 36.9 | config | model | log |
RetinaNet | FPG | 50e | 20.8 | - | 40.5 | - | config | model | log |
RetinaNet | FPG-chn128 | 50e | 19.9 | - | 40.3 | - | config | model | log |
Note: Chn128 means to decrease the number of channels of features and convs from 256 (default) to 128 in
Neck and BBox Head, which can greatly decrease memory consumption without sacrificing much precision.
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》