luo3300612/Visualizer

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1269 stars · 92 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A lightweight Python library that extracts attention maps and other local variables from deep inside PyTorch models for visualization. It works by decorating the attention function with a get_local decorator that captures named local variables via bytecode manipulation, non-invasively and without touching model code.

Use cases

• visualize attention maps from a vision transformer
• extract attention weights from a pytorch model without registering hooks
• get intermediate outputs from deeply nested transformer blocks
• capture all attention maps across transformer layers at once
• debug what attention heads look at in a trained model
• grab nested local variables from pytorch model functions non-invasively

When to choose

• You use PyTorch and need attention maps from Transformer-style models like ViT where the modules are buried in nn.Sequential and hard to address by name
• You want a zero-code-change approach so the same decorated model can be used for both training and visualization
• You need to pull out any named intermediate variable from a model function, not just attention maps

When to avoid

• You work with TensorFlow, JAX, or other non-PyTorch frameworks
• You already know your module names and simple register_forward_hook calls are enough
• You need a full-featured, actively maintained model-interpretability suite rather than a small single-purpose tool

Facets

library · maturity stable

deep-learning machine-learning data-visualization deep-learning machine-learning data-visualization artificial-intelligence python pytorch transformer attention-map interpretability decorator model-debugging explainable-ai vision-transformer hooks bytecode

Member repositories

For agents

markdown · JSON · MCP: product_card(name="luo3300612/Visualizer")