pytorch-metric-learning
quaterion
| pytorch-metric-learning | quaterion | |
|---|---|---|
| 3 | 4 | |
| 5,770 | 624 | |
| - | 2.2% | |
| 7.9 | 2.3 | |
| about 1 month ago | about 1 month ago | |
| Python | Python | |
| MIT License | Apache License 2.0 |
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.
pytorch-metric-learning
-
Similarity Learning lacks a framework. So we built one
Not a full featured framework, but pytorch-metric-learning has data loaders, lossess, etc. to facilitate similarity learning: https://github.com/KevinMusgrave/pytorch-metric-learning
Disclaimer: I've made some contributions to it.
-
[R][D] VAE Embedding Space - Can we force it to learn a metric?
You can use the triplet loss together with the Gaussian prior. It will be zero centered though and the clusters are not as separated when you use the triplet loss only.There are many alternative to the triplet loss, in case it needs to be a metric: https://github.com/KevinMusgrave/pytorch-metric-learning
-
[D] Similar Image Retrieval
This repo provides the tools and examples needed to build such a model: https://github.com/KevinMusgrave/pytorch-metric-learning
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
What are some alternatives?
dino - PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
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
lightly - A python library for self-supervised learning on images.
similarity - TensorFlow Similarity is a python package focused on making similarity learning quick and easy.
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
qdrant - Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
byol-pytorch - Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch
kervolution - Kervolution Library in PyTorch (CVPR 2019 Oral)
autogluon - Fast and Accurate ML in 3 Lines of Code
CEBRA - Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
simsiam-cifar10 - Code to train the SimSiam model on cifar10 using PyTorch
txtai - 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows