关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
PaddlePaddle
/
PaddleSeg
mirror of https://github.com/PaddlePaddle/PaddleSeg
Not watched
5
2
Fork 14
Code
Releases 20 Wiki Activity
Issues 0 Datasets Model Cloudbrain
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.
1522 Commits
25 Branches
447 MiB
3071 Download
 
 
 
 
 
 
Tree: v2.6.0
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'v2.6.0'
${ noResults }
PaddleSeg/configs/ocrnet
LutaoChu e13498b34a
[HumanSeg] Add PP-HumanSeg14K dataset (#1708) 		2 years ago
..
README.md Update model links 3 years ago
ocrnet_hrnetw18_cityscapes_1024x512_160k.yml Refactor learning rate config to support more lr strategies. 3 years ago
ocrnet_hrnetw18_cityscapes_1024x512_160k_lovasz_softmax.yml Refactor learning rate config to support more lr strategies. 3 years ago
ocrnet_hrnetw18_road_extraction_768x768_15k.yml Refactor learning rate config to support more lr strategies. 3 years ago
ocrnet_hrnetw18_road_extraction_768x768_15k_lovasz_hinge.yml Refactor learning rate config to support more lr strategies. 3 years ago
ocrnet_hrnetw18_voc12aug_512x512_40k.yml Refactor learning rate config to support more lr strategies. 3 years ago
ocrnet_hrnetw48_cityscapes_1024x512_40k.yml [HumanSeg] Add Semantic Connectivity-aware Learning and release teleconferencing dataset (#1685) 2 years ago
ocrnet_hrnetw48_cityscapes_1024x512_40k_SCL.yml [HumanSeg] Add PP-HumanSeg14K dataset (#1708) 2 years ago
ocrnet_hrnetw48_cityscapes_1024x512_160k.yml Refactor learning rate config to support more lr strategies. 3 years ago
ocrnet_hrnetw48_voc12aug_512x512_40k.yml make dygraph as home page 3 years ago

README.md

Object-Contextual Representations for Semantic Segmentation

Reference

Yuan, Yuhui, Xilin Chen, and Jingdong Wang. "Object-contextual representations for semantic segmentation." arXiv preprint arXiv:1909.11065 (2019).

Performance

CityScapes

Model Backbone Resolution Training Iters mIoU mIoU (flip) mIoU (ms+flip) Links
OCRNet HRNet_w18 1024x512 160000 80.67% 81.21% 81.30% model | log | vdl
OCRNet HRNet_w48 1024x512 160000 82.15% 82.59% 82.85% model | log | vdl

Pascal VOC 2012 + Aug

Model Backbone Resolution Training Iters mIoU mIoU (flip) mIoU (ms+flip) Links
OCRNet HRNet_w18 512x512 40000 75.76% 76.39% 77.95% model | log | vdl
OCRNet HRNet_w48 512x512 40000 79.98% 80.47% 81.02% model | log | vdl
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

飞桨高性能图像分割开发套件，端到端完成从训练到部署的全流程图像分割应用。

https://github.com/PaddlePaddle/PaddleSeg

Python Markdown Text Shell Java other

Contributors (25+)
All

Please read the following content carefully:

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》

Agree and continue
Disagree, exit