Hugging Face's logo

PrakhAI
/
AIPlane3

Model card Files
xet
Community
1
PrakhAI commited on
Commit
143fb72
·
1 Parent(s): 4f30080

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -12
README.md CHANGED
@@ -5,7 +5,7 @@ datasets:
5
 
6
  | Generated | Real (for comparison) |
7
  | ----- | --------- |
8
- | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/VXw25fJbHok5eZTQcn3Kd.png) | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/Kj0lbfg5P5fTuG6eawdE8.png) |
9
 
10
  This GAN model is trained on the [FGVC Aircraft](https://www.robots.ox.ac.uk/~vgg/data/fgvc-aircraft/) dataset. The model uses [Progressive Growing](https://arxiv.org/pdf/1710.10196.pdf) with [Spectral Normalization](https://arxiv.org/pdf/1802.05957.pdf).
11
 
@@ -21,24 +21,18 @@ A significant improvement over https://huggingface.co/PrakhAI/AIPlane2 is the el
21
  | - | - |
22
  | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/Vs1Dks67tteJGA2EaVMjW.png) | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/fz_Gv0UIYh_Z1GZ2TrCW1.png) |
23
 
24
- # Image Quality
25
 
26
- The model, while generating several high quality images of Airplanes, also generates poor quality images.
27
 
28
- A total of 400 generated images were labeled by hand as either desirable (151) or undesirable (249).
29
 
30
- | Sample desirable outputs | Sample undesirable outputs |
31
- | --------- | ------------ |
32
- | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/YkIba5DXFIGwVX0fs1Han.png) | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/p4cU-1LfNbmdePOUk-CF5.png) |
33
 
34
- # Latent Space Interpolation
35
 
36
- Latent Space Interpolation can an educational exercise to get deeper insight into the model.
37
 
38
- It can be observed below that several aspects of the generated image such as the color of the sky, grounded-ness of the plane, as well as the plane shape and color are frequently continuous through the latent space.
 
39
 
40
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/Hx_a5OzCwdWBIvH-7hvR3.png)
41
 
42
  # Training Progression
43
 
44
- <video controls width="50%" src="https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/o2NDDMQPhdEY5Vc96b31G.mp4"></video>
 
5
 
6
  | Generated | Real (for comparison) |
7
  | ----- | --------- |
8
+ | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/7pYCY8gRHLcOs9eNaq09m.png) | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/NH8orTN9e0BwKE2KntgAv.png) |
9
 
10
  This GAN model is trained on the [FGVC Aircraft](https://www.robots.ox.ac.uk/~vgg/data/fgvc-aircraft/) dataset. The model uses [Progressive Growing](https://arxiv.org/pdf/1710.10196.pdf) with [Spectral Normalization](https://arxiv.org/pdf/1802.05957.pdf).
11
 
 
21
  | - | - |
22
  | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/Vs1Dks67tteJGA2EaVMjW.png) | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/fz_Gv0UIYh_Z1GZ2TrCW1.png) |
23
 
24
+ # Samples
25
 
 
26
 
 
27
 
28
+ # ProGAN
 
 
29
 
 
30
 
 
31
 
32
+ # Spectral Normalization
33
+
34
 
 
35
 
36
  # Training Progression
37
 
38
+ <video controls src="https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/QCjxqTjEXUbRXnPjStRAb.mp4"></video>