mirror of
https://git.mirrors.martin98.com/https://github.com/xuebinqin/U-2-Net
synced 2025-08-17 12:25:52 +08:00
input size and readme
This commit is contained in:
parent
be04a30115
commit
3497b58b14
@ -11,7 +11,7 @@ __Contact__: xuebin[at]ualberta[dot]ca
|
|||||||
|
|
||||||
**(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 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 [BASNet](https://github.com/NathanUA/BASNet) and U^2-Net. The [demo video](https://twitter.com/cyrildiagne/status/1256916982764646402) has achieved over **5M** views, which is phenomenal and show us more probabilities of SOD.
|
**(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** and [**BASNet**](https://github.com/NathanUA/BASNet). The [demo video](https://twitter.com/cyrildiagne/status/1256916982764646402) in twitter has achieved over **5M** views, which is phenomenal and shows us more probabilities of SOD.
|
||||||
|
|
||||||
## U^2-Net Results (173.6 MB)
|
## U^2-Net Results (173.6 MB)
|
||||||
|
|
||||||
|
Loading…
x
Reference in New Issue
Block a user