Import Deep Learning Models

by matlab

Import Deep Learning Models is an AI Engineering skill for Claude Code, published by matlab in matlab-agentic-toolkit.

938 stars115 forkson matlab/matlab-agentic-toolkitAdded 2026/08/21+2% in starsRepository updated 2026/08/13

View source on GitHub Download repo ZIP

agent-skillsclaude-codecodex-pluginengineering-agentsgithub-copilotmatlabmatlab-mcp-server

Install in seconds

Install Import Deep Learning Models

Copy Import Deep Learning Models into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/matlab/matlab-agentic-toolkit/tree/main/skills-catalog/ai-and-statistics/matlab-import-external-ai-model ~/.claude/skills/matlab-import-external-ai-model

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/matlab/matlab-agentic-toolkit.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills-catalog/ai-and-statistics/matlab-import-external-ai-model/SKILL.md in matlab/matlab-agentic-toolkit
Installs to: ~/.claude/skills/matlab-import-external-ai-model
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Import Deep Learning Models does

Import Deep Learning Models brings PyTorch, ONNX, and Keras/TensorFlow models into MATLAB as dlnetwork objects. Use it when converting .pt2, .pt, .onnx, or .keras files and when checking import errors or output validation.

Import Deep Learning Models is cataloged under AI Engineering on DirSkills. Import Deep Learning Models comes from a repository tagged agent-skills, claude-code, codex-plugin, engineering-agents and github-copilot.

Documentation

README

Excerpt

Import Deep Learning Models into MATLAB

Import trained PyTorch, ONNX, or Keras 3 models into MATLAB as dlnetwork objects and verify numerical correctness.

When to Use

User wants to import a deep learning model from PyTorch, ONNX, or Keras/TensorFlow
User has .pt2, .pt, .onnx, or .keras files to bring into MATLAB
User mentions importNetworkFromPyTorch, importNetworkFromONNX, importNetworkFromKeras, or importNetworkFromTensorFlow
User mentions torch.export.export, torch.jit.trace, PyTorchInputSizes, InputDataFormats, or matlabsaver
User encounters import errors, unsupported operator warnings, uninitialized networks, or 0 learnables after import
User wants to validate that an imported model matches the source framework's outputs

This is the opening of the README. Read the full README on GitHub.

Commands Import Deep Learning Models provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/matlab-train-network
/matlab-deploy-embedded-ai

Frequently asked about Import Deep Learning Models

What else does matlab publish alongside Import Deep Learning Models?
Import Deep Learning Models is one of 25 skills that DirSkills catalogs from matlab/matlab-agentic-toolkit, the repository it ships in. Its siblings there include Aerospace Fundamentals, Build RoadRunner Scenario From OpenSCENARIO and Compute Aerospace Environment. Each one is a separate skill with its own page in this directory, installs the same way Import Deep Learning Models does, and is maintained by matlab in that same repository. The rest of the collection is listed on the matlab/matlab-agentic-toolkit page.
How does Import Deep Learning Models compare to other AI Engineering skills?
Import Deep Learning Models ranks #1445 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Import Deep Learning Models against them. Open each page to compare what they document and how they install.