Downloads · 30 days
0
Image-regenerator-model
hurairamuzammal/Image-regenerator-model
Image-regenerator-model is a machine learning model from hurairamuzammal. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
AI Assignment 02 | Generative AI AI4009 | FAST-NUCES Spring 2026
Access
Public
Updated Mar 9, 2026
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth431 MB · 99%
At a glance
- License
- mit
- Access
- Public
- Created
- Mar 8, 2026
- Updated
- Mar 9, 2026
- SHA
- 1d550823
Model card
From the Hugging Face model README
MAE – Masked Autoencoder Image Reconstruction
AI Assignment 02 | Generative AI AI4009 | FAST-NUCES Spring 2026
This Space demonstrates a self-supervised Masked Autoencoder (MAE) trained on TinyImageNet.
How it works
- Upload any image.
- Adjust the masking ratio slider (default 75 %).
- Click Reconstruct to see:
- The original (resized to 224 × 224)
- The masked input (grey patches = hidden)
- The MAE reconstruction
Architecture
| Component | Spec |
|---|---|
| Encoder | ViT-Base B/16, embed=768, depth=12, heads=12, ~86M params |
| Decoder | ViT-Small S/16, embed=384, depth=12, heads=6, ~22M params |
| Patch size | 16 × 16 |
| Visible patches | 25 % (49 of 196) |
| Loss | MSE on masked patches only |
| Training | AdamW + CosineAnnealing, Mixed Precision, 50 epochs |
Setup
Upload mae_tiny_imagenet.pth (the trained weights) to the root of this Space.
The file is generated by running the Kaggle notebook AI_ASS02_XXF_YYYY.ipynb.
- License
- mit
- Created
- Mar 8, 2026
- Updated
- Mar 9, 2026