quaterion
retomaton
| quaterion | retomaton | |
|---|---|---|
| 4 | 1 | |
| 625 | 64 | |
| 2.4% | - | |
| 2.3 | 0.0 | |
| about 2 months ago | almost 2 years ago | |
| Python | Python | |
| Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
quaterion
-
Similarity Learning lacks a framework. So we built one
PML is a great collection of implementations, but not the best framework. Also you can use PML with Quaterion: https://github.com/qdrant/quaterion/blob/master/examples/tra...
- Show HN: Quaterion – x100 faster fine-tuning of similarity learning models
-
[N] Quaterion, a blazingly fast framework for similarity learning.
Just released. Quaterion — an open source framework for training and fine-tuning similarity learning models. It enables you to train models significantly (100x) faster, and iterate over experiments in minutes instead of hours even with a laptop GPU. It takes advantage of the PyTorch Lightning backend to make a flexible and scalable learning pipeline. GitHub https://github.com/qdrant/quaterion
-
Introducing the Quaterion: a framework for fine-tuning similarity learning models
Quaterion on GitHub: https://github.com/qdrant/quaterion
retomaton
What are some alternatives?
lightning-flash - Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains
RETRO-pytorch - Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
similarity - TensorFlow Similarity is a python package focused on making similarity learning quick and easy.
RetGen
qdrant - Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
VeRyPy - A python library with implementations of 15 classical heuristics for the capacitated vehicle routing problem.
pytorch-metric-learning - The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
beir - A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
kervolution - Kervolution Library in PyTorch (CVPR 2019 Oral)
TSP_Solver - Python code for visualizations of algorithms that provide approximate solutions to TSP along with two lower bound approximations
CEBRA - Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
robo-vln - Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"