geninhu commited on
Commit
055251f
1 Parent(s): f2de1b6

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +47 -0
README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - huggan
4
+ - gan
5
+ # See a list of available tags here:
6
+ # https://github.com/huggingface/hub-docs/blob/main/js/src/lib/interfaces/Types.ts#L12
7
+ # task: unconditional-image-generation or conditional-image-generation or image-to-image
8
+ license: mit
9
+ ---
10
+
11
+ # Generate fauvism still life image using FastGAN
12
+
13
+ ## Model description
14
+
15
+ [FastGAN model](https://arxiv.org/abs/2101.04775) is a Generative Adversarial Networks (GAN) training on a small amount of high-fidelity images with minimum computing cost. Using a skip-layer channel-wise excitation module and a self-supervised discriminator trained as a feature-encoder, the model was able to converge after some hours of training for either 100 high-quality images or 1000 images datasets.
16
+
17
+ This model was trained on a dataset of 272 high-quality images of aurora.
18
+
19
+
20
+ #### How to use
21
+
22
+ ```python
23
+ # You can include sample code which will be formatted
24
+ ```
25
+
26
+ #### Limitations and bias
27
+
28
+ * Converge faster and better with small datasets (less than 1000 samples)
29
+
30
+ ## Training data
31
+
32
+ [few-shot-aurora](https://huggingface.co/datasets/huggan/few-shot-aurora)
33
+
34
+ ## Generated Images
35
+
36
+ ![Example image](example.png)
37
+
38
+ ### BibTeX entry and citation info
39
+
40
+ ```bibtex
41
+ @article{FastGAN,
42
+ title={Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis},
43
+ author={Bingchen Liu, Yizhe Zhu, Kunpeng Song, Ahmed Elgammal},
44
+ journal={ICLR},
45
+ year={2021}
46
+ }
47
+ ```