eamonn-zh/torchmetrics_ext

Extentions of TorchMetrics

39
/ 100
Emerging

This project helps researchers and developers working with 3D visual data accurately evaluate the performance of their machine learning models for tasks like 3D Visual Grounding and 3D Object Detection. It takes the model's predictions (e.g., bounding box coordinates or selected object indices) and compares them against ground truth data, outputting standardized metrics such as accuracy or F1-scores. This tool is designed for practitioners building and testing advanced computer vision systems.

Available on PyPI.

Use this if you are developing or evaluating machine learning models that interpret and interact with 3D visual environments, specifically for tasks like referring to objects in 3D scenes based on descriptions or detecting objects within 3D scans.

Not ideal if your primary focus is on 2D image processing, traditional computer vision tasks without a 3D component, or if you are not using PyTorch for your model development.

3D-computer-vision visual-grounding object-detection model-evaluation spatial-reasoning
Maintenance 10 / 25
Adoption 4 / 25
Maturity 25 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

Apache-2.0

Last pushed

Jan 24, 2026

Commits (30d)

0

Dependencies

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/eamonn-zh/torchmetrics_ext"

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