lab-v2/PyEDCR
PyEDCR is a metacognitive neuro-symbolic method for learning error detection and correction rules in deployed ML models using combinatorial sub-modular set optimization
This tool helps machine learning engineers identify and fix mistakes in their deployed AI models, especially those classifying data with multiple categories or hierarchies, like images with both fine-grain and coarse-grain labels. You provide your existing machine learning model and some data, and it outputs rules that explain why your model made an error and suggests how to correct it. It's designed for data scientists and ML practitioners who need to improve the reliability and explainability of their classification models.
No commits in the last 6 months.
Use this if you need to understand why your machine learning model is making errors and want to automatically generate rules to detect and correct those specific mistakes, particularly in hierarchical classification tasks.
Not ideal if your primary goal is to train a new model from scratch or if you are not working with classification models that might have hierarchical outputs.
Stars
7
Forks
1
Language
Python
License
MIT
Category
Last pushed
Feb 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lab-v2/PyEDCR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
torchgeo/torchgeo
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
terrastackai/terratorch
A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).
DataverseLabs/pyinterpolate
Kriging | Poisson Kriging | Variogram Analysis
OSGeo/grass
GRASS - free and open-source geospatial processing engine
sentinel-hub/eo-learn
Earth observation processing framework for machine learning in Python