You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
# emojigan
2
2
Emoji Dataset I compiled (4000+ emojis) 🤩😫 [link](https://drive.google.com/drive/folders/1kqKJU3o8v3mIS2F4kpE_kRBUjYXUncSm)
3
-
3
+

4
4
## Motivation
5
5
This project was to explore just what happens when you train a simple GAN model (DCGAN) on a toy dataset that you know pretty much how every data sample looks like. Will the GAN create completely novel emojis? Or will it memorize? How will it create these emojis? Will it vary the color? Compose two or more emojis together? These are the types of questions I wanted to find out... I discovered several examples of both memorization and completely new emojis shown here:
0 commit comments