| --- |
| license: apache-2.0 |
| task_categories: |
| - unconditional-image-generation |
| tags: |
| - conditional-vae |
| - generative-model |
| - pytorch |
| - gradio |
| --- |
| |
| # GlyphForge CVAE |
|
|
| GlyphForge is a compact conditional variational autoencoder that generates 8x8 |
| handwritten digits. A requested digit label conditions the decoder while an |
| eight-dimensional Gaussian latent captures style. |
|
|
| The benchmark measures: |
|
|
| - held-out reconstruction MSE; |
| - KL divergence to the unit-Gaussian prior; |
| - generated-class fidelity through the frozen Tiny Vision classifier; |
| - within-class sample diversity. |
|
|
| ## Reproduce |
|
|
| ```powershell |
| uv run python projects/tiny-vision-foundry/prepare_data.py |
| uv run python projects/glyph-forge-cvae/train.py |
| ``` |
|
|
| The saved sample grid and Gradio app are model outputs, not hand-authored examples. |
|
|
| ## Verified results |
|
|
| - Parameters: **9,504** |
| - Latent dimensions: **8** |
| - Held-out reconstruction MSE: **0.02394** |
| - Mean held-out KL divergence: **0.3978** |
| - Conditional samples evaluated: **1,000** |
| - Frozen-judge class fidelity: **99.90%** |
|
|
| Nine digit classes achieved 100% judge fidelity; digit `1` achieved 99%. Every class |
| had nonzero mean pixel variance across its 100 samples, ranging from 0.0066 to 0.0168. |
| The judge is the 2,198-parameter Tiny Vision labels-only student with 98.52% accuracy |
| on real held-out images, so this metric measures recognizability to that specific |
| classifier rather than human perceptual quality. |
|
|
