AI/U-2-Net
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/xuebinqin/U-2-Net synced 2025-08-16 12:05:53 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/NathanUA/U-2-Net

Browse Source
This commit is contained in:
Nathan Qin 2020-05-27 21:33:16 -06:00
commit 0f7a66ca5e
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -14,13 +14,13 @@ __Contact__: xuebin[at]ualberta[dot]ca
## Updates !!!
**(2020-May-16)** The official paper of our **U^2-Net (U square net)** ([**PDF in elsevier**](https://www.sciencedirect.com/science/article/pii/S0031320320302077?dgcid=author)) is now available. If you are not able to access that, please feel free to drop me an email.
**(2020-May-18)** The official paper of our **U^2-Net (U square net)** ([**PDF in elsevier**(free until July 5 2020)](https://www.sciencedirect.com/science/article/pii/S0031320320302077?dgcid=author), [**PDF in arxiv**](http://arxiv.org/abs/2005.09007)) is now available. If you are not able to access that, please feel free to drop me an email.
**(2020-May-16)** We fixed the upsampling issue of the network. Now, the model should be able to handle **arbitrary input size**. (Tips: This modification is to facilitate the retraining of U^2-Net on your own datasets. When using our pre-trained model on SOD datasets, please keep the input size as 320x32 to guarantee the performance.)
**(2020-May-16)** We highly appreciate **Cyril Diagne** for building this fantastic AR project: [**AR Copy and Paste**](https://github.com/cyrildiagne/ar-cutpaste) using our **U^2-Net** (Qin *et al*, PR 2020) and [**BASNet**](https://github.com/NathanUA/BASNet)(Qin *et al*, CVPR 2019). The [**demo video**](https://twitter.com/cyrildiagne/status/1256916982764646402) in twitter has achieved over **5M** views, which is phenomenal and shows us more application probabilities of SOD.
## U^2-Net Results (173.6 MB)
## U^2-Net Results (176.3 MB)
![U^2-Net Results](figures/u2netqual.png)
@ -42,7 +42,7 @@ glob
```
git clone https://github.com/NathanUA/U-2-Net.git
```
2. Download the pre-trained model [u2net.pth (173.6 MB)](https://drive.google.com/file/d/1ao1ovG1Qtx4b7EoskHXmi2E9rp5CHLcZ/view?usp=sharing) or [u2netp.pth (4.7 MB)](https://drive.google.com/file/d/1rbSTGKAE-MTxBYHd-51l2hMOQPT_7EPy/view?usp=sharing) and put it into the dirctory './saved_models/u2net/' and './saved_models/u2netp/'
2. Download the pre-trained model [u2net.pth (176.3 MB)](https://drive.google.com/file/d/1ao1ovG1Qtx4b7EoskHXmi2E9rp5CHLcZ/view?usp=sharing) or [u2netp.pth (4.7 MB)](https://drive.google.com/file/d/1rbSTGKAE-MTxBYHd-51l2hMOQPT_7EPy/view?usp=sharing) and put it into the dirctory './saved_models/u2net/' and './saved_models/u2netp/'
3. Cd to the directory 'U-2-Net', run the train or inference process by command: ```python u2net_train.py```
or ```python u2net_test.py``` respectively. The 'model_name' in both files can be changed to 'u2net' or 'u2netp' for using different models.