AI/U-2-Net
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/xuebinqin/U-2-Net synced 2025-08-05 20:46:13 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

human seg

Browse Source
This commit is contained in:
NathanUA 2021-02-06 20:30:15 -07:00
parent e0d6667846
commit 7e7fd18c12
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -17,7 +17,7 @@ __Contact__: xuebin[at]ualberta[dot]ca
**(2021-Feb-06)** Since some people raised the issue of human segmentation using U^2-Net, we trained another model for human segemntation based on [**Supervisely Person Dataset**](https://supervise.ly/explore/projects/supervisely-person-dataset-23304/datasets). To run the human segmentation model, please first downlowd the [**u2net_human_seg.pth**](https://drive.google.com/file/d/1-Yg0cxgrNhHP-016FPdp902BR-kSsA4P/view?usp=sharing) model weights and start the inference by command: ```python u2net_human_seg_test.py```. <br/>
[**Notes: Due to the labeling accuracy of the Supervisely Person Dataset, the human segmentation model here won't give you hair level accuracy. But it should be more robust than u2net trained with DUTS-TR dataset on human segmentation task. It can be used for human portrait segmentation, human body segmentation, etc.**](https://github.com/NathanUA/U-2-Net)<br/>
![Human Image Segmentation](figures/human_seg)
![Human Image Segmentation](figures/human_seg.png) <br/>
![Human Video](figures/human_seg_video.gif)
![Human Video Results](figures/human_seg_results.gif)