pietrolesci/energizer
An active learning library for Pytorch based on Lightning-Fabric.
This is a framework for machine learning engineers and researchers who train deep learning models using PyTorch. It helps efficiently label data by iteratively selecting the most informative unlabelled data points for annotation. You input a PyTorch-Lightning model and a dataset, and it outputs a highly accurate model using fewer labels than traditional training.
No commits in the last 6 months.
Use this if you need to train high-performing deep learning models with limited labelled data, especially when data annotation is expensive or time-consuming.
Not ideal if your dataset is already fully labelled and you don't need to optimize the data annotation process.
Stars
79
Forks
11
Language
Python
License
Apache-2.0
Category
Last pushed
May 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pietrolesci/energizer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pykt-team/pykt-toolkit
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
microsoft/archai
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
google-research/morph-net
Fast & Simple Resource-Constrained Learning of Deep Network Structure
AI-team-UoA/pyJedAI
An open-source library that leverages Python’s data science ecosystem to build powerful...
IDEALLab/EngiBench
Benchmarks for automated engineering design