Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Github Repo https://github.com/kevalpithadiya/Diffusion-Models
|
| 2 |
+
|
| 3 |
+
# Diffusion Models
|
| 4 |
+
This work was part of a term paper / project for the UMC203 Introduction to AI and ML course at IISc.
|
| 5 |
+
|
| 6 |
+
## Contributors
|
| 7 |
+
- Om Prakash Choudhary
|
| 8 |
+
- Himesh Kumar Anant
|
| 9 |
+
- Jithendra Rao Kasibhatla
|
| 10 |
+
- Keval Pithadiya
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
## Models Trained
|
| 14 |
+
We trained Denoising Diffusion Probabilitic Models using the HuggingFace `diffusers` library for the clean image prediction and the noise prediction objectives on the below datasets and image sizes
|
| 15 |
+
|
| 16 |
+
- CIFAR10 (32x32)
|
| 17 |
+
- CelebA (32x32)
|
| 18 |
+
- CelebA (128x128)
|
| 19 |
+
- MNIST (32x32)
|
| 20 |
+
|
| 21 |
+
The trained models can be downloaded from this Google Drive link:
|
| 22 |
+
https://drive.google.com/drive/folders/1HmLK4hkkI6-Fl6vaHyX05PBe8U2FWl5E?usp=drive_link
|