xinntao/ESRGAN
1
1
Fork 0
mirror of https://github.com/xinntao/ESRGAN.git synced 2024-08-17 08:30:32 +03:00
Code Issues Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Xintao 2018-09-06 14:58:27 +08:00 committed by GitHub
parent ffd33e1f36
commit ce16ee8e30
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
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

@ -134,7 +134,7 @@ We find that residual scaling and smaller initialization can help to train a ver
## The influence of training patch size
We observe that training a deeper network benefits from a larger patch size. Moreover, the deeper model achieves more improvement (∼0.12dB) than the shallower one (∼0.04dB) since larger model capacity is capable of taking full advantage of
larger training patch size.
larger training patch size. (Evaluated on Set5 dataset with RGB channels.)
<p align="center">
<img height="250" src="figures/patch_a.png">
<img height="250" src="figures/patch_b.png">