model-equivariance-auditor

Community

Verify your model's symmetry guarantees.

Authorlyndonkl
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill ensures that your implemented neural network models correctly adhere to their intended symmetries, preventing subtle bugs that can lead to poor training and inconsistent results.

Core Features & Use Cases

  • Equivariance Verification: Run end-to-end tests to confirm if your model respects specified symmetries (e.g., rotation, translation).
  • Layer-wise Debugging: Isolate and identify specific layers that violate equivariance properties.
  • Gradient Symmetry Check: Verify that the model's gradients also respect the intended symmetries, crucial for stable training.
  • Use Case: After implementing a new 3D convolutional neural network for molecular property prediction, use this Skill to rigorously test if its predictions change predictably when the input molecule is rotated.

Quick Start

Use the model-equivariance-auditor skill to run end-to-end equivariance tests on your PyTorch model.

Dependency Matrix

Required Modules

torchnumpyscipy

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: model-equivariance-auditor
Download link: https://github.com/lyndonkl/claude/archive/main.zip#model-equivariance-auditor

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.