Show HN: X.infer-Framework agnostic computer vision inference

[dnth]

I spent the past 3 weeks building x.infer, a Python package that lets you run computer vision inference on a framework of choice.

It currently supports models from transformers, Ultralytics, Timm, vLLM and Ollama. Combined, this covers over 1000+ computer vision models. You can easily add your own model.

Repo - https://github.com/dnth/x.infer

Colab quickstart - https://colab.research.google.com/github/dnth/x.infer/blob/m...

Why did I make this?

It's mostly just for fun. I wanted to practice some design pattern principles I picked up from the past. The code is still messy though but it works.

Also, I enjoy playing around with new vision models, but not so much learning about the framework it's written with.

I'm working on this during my free time. Contributions/feedback are more than welcome! Hope this also helps you (especially newcomers) to experiment and play around with new vision models.