BARL-SSL/reptrix
Library that provides metrics to assess representation quality
This library helps machine learning researchers and engineers evaluate how well their deep learning models learn meaningful features from images. You input features extracted from your image data using a pretrained model, and it outputs numerical scores like alpha, RankMe, and LiDAR. These scores indicate the quality, capacity, and separability of the learned representations, especially for models trained with self-supervised learning.
No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning practitioner working with computer vision models, particularly those trained with self-supervised learning, and need to quantitatively assess the quality and interpretability of your learned representations.
Not ideal if your primary goal is to train models from scratch or if you are not working with deep learning models and learned representations in computer vision.
Stars
24
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 05, 2025
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BARL-SSL/reptrix"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVIDIA-Merlin/HugeCTR
HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training
shenweichen/DeepCTR-Torch
【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.
shenweichen/DeepCTR
Easy-to-use,Modular and Extendible package of deep-learning based CTR models .
UlionTse/mlgb
MLGB is a library that includes many models of CTR Prediction & Recommender System by TensorFlow...
cnkuangshi/LightCTR
Lightweight and Scalable framework that combines mainstream algorithms of Click-Through-Rate...