OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io/
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
杨培文 (Yang Peiwen)
e0cb8666a5
|
3 years ago | |
|---|---|---|
| .. | ||
| README.md | 3 years ago | |
| faster_rcnn_r50_fpn_fp16_1x_coco.py | 5 years ago | |
| mask_rcnn_r50_fpn_fp16_1x_coco.py | 5 years ago | |
| mask_rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco.py | 4 years ago | |
| mask_rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco.py | 4 years ago | |
| metafile.yml | 3 years ago | |
| retinanet_r50_fpn_fp16_1x_coco.py | 5 years ago | |
README.md
Mixed Precision Training
Introduction
@article{micikevicius2017mixed,
title={Mixed precision training},
author={Micikevicius, Paulius and Narang, Sharan and Alben, Jonah and Diamos, Gregory and Elsen, Erich and Garcia, David and Ginsburg, Boris and Houston, Michael and Kuchaiev, Oleksii and Venkatesh, Ganesh and others},
journal={arXiv preprint arXiv:1710.03740},
year={2017}
}
Results and Models
| Architecture | Backbone | Style | Conv | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
|---|---|---|---|---|---|---|---|---|---|---|
| Faster R-CNN | R-50 | pytorch | - | 1x | 3.4 | 28.8 | 37.5 | - | config | model | log |
| Mask R-CNN | R-50 | pytorch | - | 1x | 3.6 | 24.1 | 38.1 | 34.7 | config | model | log |
| Mask R-CNN | R-50 | pytorch | dconv(c3-c5) | 1x | 3.0 | 41.9 | 37.5 | config | model | log | |
| Mask R-CNN | R-50 | pytorch | mdconv(c3-c5) | 1x | 3.1 | 42.0 | 37.6 | config | model | log | |
| Retinanet | R-50 | pytorch | - | 1x | 2.8 | 31.6 | 36.4 | config | model | log |