| --- |
| license: mit |
| pipeline_tag: unconditional-image-generation |
| library_name: diffusers |
| tags: |
| - image-generation |
| - unconditional-diffusion |
| - indian-sign-language |
| --- |
| |
| # ISL Unconditional Diffusion |
|
|
| An unconditional DDPM trained from scratch to generate 128×128 RGB images of Indian Sign Language hand gestures. |
|
|
| The model learns the overall distribution of ISL gesture images without receiving a class label during training or inference. |
|
|
| The complete implementation and experiments are available in the [GitHub repository](https://github.com/MahadevBalla/isl-diffusion). |
|
|
| ## Model |
|
|
| - DDPM with UNet2D architecture |
| - 128×128 resolution |
| - RGB images |
| - Unconditional generation |
| - EMA weights |
|
|
| ## Training |
|
|
| - Dataset: 42,000 images (1,200 images per class × 35 classes) |
| - Noise schedule: cosine |
| - Batch size: 64 |
| - Learning rate: 1e-4 |
| - Mixed precision: fp16 |
| - Training steps: 65,000 |
| - EMA decay: 0.9999 |
| - Data augmentation: enabled |
|
|
| ## Sampling |
|
|
| - Default sampler: DDIM |
| - Training diffusion timesteps: 1,000 |
| - Routine inference steps: 100 |
| - Evaluation inference steps: 50 |
| - Random seed: 42 |
|
|
| ## Results |
|
|
| The unconditional model achieves an FID of 86.06 under the reported evaluation setting. |
|
|
