AI Blocks › Connect AI to your tools
Python vision model connector
Give it a vision model repo on GitHub. Get a MATLAB function that runs it on your images.
Python vision model connector is a free AI skill for the job "Connect AI to your tools". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · BSD 2 Clause licence · Made by MathWorks · Level: advanced
Made by MathWorks. See the original on GitHub; we copied it as it is, with its licence.
What it does
A MATLAB function that runs a Python vision model on your images, so you can use tools like segmentation or depth estimation without leaving MATLAB. Give it a GitHub repository or pip package for an image model. The skill reads the repo, then builds a MATLAB interface with the MPyReq framework: a function that sends your image to the Python model and returns the result as MATLAB data. It covers models for segmentation, depth, detection, super-resolution, pose, optical flow and image generation. It does not suit audio or text models, model serving or pure MATLAB image work. You need MATLAB, Python and MPyReq set up.
You give it
- GitHub link or package name of the vision model
- Sample images
- MATLAB and Python environment details
- Model weights location (optional)
You get
- MATLAB function that calls the model
- Setup steps for the Python side
- A demo script on your sample image
- Notes on inputs and outputs
Use it when
- A new segmentation or depth model exists only as Python code.
- You work in MATLAB and want to call that model on your own images.
- You want a demo showing the model working end to end.
- You need to wrap a pip package such as Cellpose or SAM2.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run MATLAB and Python.