-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
12 changed files
with
24 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,14 @@ | ||
# Generative Adverserial Network - MNIST | ||
|
||
Generative Adverserial Networks are powerful tools for generative modeling. The new technique of training deep neural networks using adverserial networks has given generative modeling new avenues of research. | ||
|
||
To display the power of GAN's this repository hosts the code to load and train a GAN on the MNIST dataset. The results of generation can be viewed here. | ||
|
||
<img width="100" src="./gifs/0.gif"><img width="100" src="./gifs/1.gif"><img width="100" src="./gifs/2.gif"><img width="100" src="./gifs/3.gif"><img width="100" src="./gifs/4.gif"> | ||
|
||
<img width="100" src="./gifs/5.gif"><img width="100" src="./gifs/6.gif"><img width="100" src="./gifs/7.gif"><img width="100" src="./gifs/8.gif"><img width="100" src="./gifs/9.gif"> | ||
|
||
|
||
The dataset that we used is the popular MNIST dataset in the form of images: https://www.kaggle.com/scolianni/mnistasjpg | ||
|
||
Here is the link to the original paper: https://arxiv.org/abs/1406.2661 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,10 @@ | ||
import imageio | ||
|
||
for i in range(10): | ||
gif = [] | ||
path = f"samples/{i}" | ||
|
||
for filename in range(100): | ||
gif.append(imageio.imread(f"{path}/sample_epoch_{filename}.jpg")) | ||
|
||
imageio.mimsave(f"gifs/{i}.gif", gif, fps=24) |
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.