NimaBoscarino commited on
Commit
8394b1a
1 Parent(s): 61dd561

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -10
README.md CHANGED
@@ -1,15 +1,31 @@
1
  ---
2
- language:
3
- - ru
4
- - en
5
  tags:
6
- - translation
7
- license: apache-2.0
8
- datasets:
9
- - wmt19
10
  metrics:
11
- - bleu
12
- - sacrebleu
 
 
 
 
13
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
 
15
- # Some text here
 
 
1
  ---
 
 
 
2
  tags:
3
+ - face-recognition
4
+ - face-generation
5
+ - face-segmentation
6
+ - generative-adversarial-network
7
  metrics:
8
+ - L1
9
+ - PSNR
10
+ - SSIM
11
+ - FID
12
+ datasets:
13
+ - celeba-hq
14
  ---
15
+ # AOT-GAN CelebA-HQ
16
+ AOT-GAN is a model that can be used for image in-painting. The CelebA-HQ checkpoint is trained on synthetic human faces, which should make it suitable for touching up and restoring portraits.
17
+
18
+ This model was generated using [AOT-GAN-for-Inpainting](https://github.com/researchmm/AOT-GAN-for-Inpainting), cited as
19
+
20
+ ```
21
+ @inproceedings{yan2021agg,
22
+ author = {Zeng, Yanhong and Fu, Jianlong and Chao, Hongyang and Guo, Baining},
23
+ title = {Aggregated Contextual Transformations for High-Resolution Image Inpainting},
24
+ booktitle = {Arxiv},
25
+ pages={-},
26
+ year = {2020}
27
+ }
28
+ ```
29
 
30
+ ## Dataset
31
+ The CelebA-HQ dataset was created with this codebase: https://github.com/tkarras/progressive_growing_of_gans, owned by NVidia and licensed under Creative Commons Attribution-NonCommercial 4.0 International.