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 16:20:50 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

human seg

Browse Source
This commit is contained in:
NathanUA 2021-02-06 20:37:27 -07:00
parent 566213a461
commit 7f458bab6e
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

@ -19,7 +19,7 @@ __Contact__: xuebin[at]ualberta[dot]ca
(1) 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 into ``` ./saved_models/u2net_human_seg/```. <br/>
(2) Prepare the to-be-segmented images into the corresponding directory, e.g. ```./test_data/test_human_images/```. <br/>
(3) Run the inference by command: ```python u2net_human_seg_test.py``` and the results will be output into the corresponding dirctory, e.g. ```./test_data/u2net_test_human_images_results/```<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/>
[**Notes: Due to the labeling accuracy of the Supervisely Person Dataset, the human segmentation model (u2net_human_seg.pth) here won't give you hair-level accuracy. But it should be more robust than u2net trained with DUTS-TR dataset on general 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.png) <br/>
![Human Video](figures/human_seg_video.gif)