Glyph Forge Cvae

Verified project card

# 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.

Evaluation snapshot

{
  "model": "GlyphForge Conditional VAE",
  "parameters": 9504,
  "latent_dimensions": 8,
  "best_epoch": 158,
  "test": {
    "reconstruction_mse": 0.023938464456134373,
    "mean_kl": 0.3978222034595631,
    "examples": 270
  },
  "generation": {
    "judge_accuracy": 0.9990000128746033,
    "judge_accuracy_by_class": {
      "0": 1.0,
      "1": 0.9900000095367432,
      "2": 1.0,
      "3": 1.0,
      "4": 1.0,
      "5": 1.0,
      "6": 1.0,
      "7": 1.0,
      "8": 1.0,
      "9": 1.0
    },
    "mean_pixel_variance_by_class": {
      "0": 0.0066222199238836765,
      "1": 0.01683112047612667,
      "2": 0.012290791608393192,
      "3": 0.010615515522658825,
      "4": 0.011259874328970909,
      "5": 0.011659887619316578,
      "6": 0.010034985840320587,
      "7": 0.012352265417575836,
      "8": 0.011395774781703949,
      "9": 0.011373817920684814
    },
    "samples": 1000
  },
  "judge": "Tiny Vision labels-only student, 98.52% real-image test accuracy"
}

Backed-up artifact tree

• README.md
• __pycache__/app.cpython-311.pyc
• __pycache__/model.cpython-311.pyc
• app.py
• artifacts/glyph-forge-cvae/evaluation.json
• artifacts/glyph-forge-cvae/model.safetensors
• artifacts/glyph-forge-cvae/samples.png
• model.py
• requirements.txt
• train.py