hugohadfield/pytorch_image_regression

A template for doing regression from images with pytorch

38
/ 100
Emerging

This project helps machine learning practitioners predict a continuous value or vector from images, a task known as image regression. It takes a collection of images and a CSV file mapping each image to its target numeric values, then outputs a trained model capable of making predictions on new images. This is useful for data scientists and ML engineers working on computer vision tasks that go beyond simple categorization.

No commits in the last 6 months.

Use this if you need a clear, basic example to set up an image regression task in PyTorch, especially if you're finding it hard to get started with predicting continuous values instead of categories from images.

Not ideal if you are looking for an out-of-the-box solution with advanced features or state-of-the-art model architectures for complex, production-ready systems.

computer-vision machine-learning-engineering predictive-modeling data-science image-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

41

Forks

7

Language

Python

License

MIT

Last pushed

Oct 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hugohadfield/pytorch_image_regression"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.