Confusezius/Deep-Metric-Learning-Baselines
A PyTorch pipeline implementing deep metric learning methods including triplet loss, margin loss, and proxy-based losses for image similarity tasks.
Not currently ranked — collecting fresh signals.
star history
This repository provides an extendable PyTorch framework for deep metric learning, implementing various loss functions (Triplet, Margin, ProxyNCA, N-Pair) and sampling strategies (random, softhard, semihard, distance). It includes dataloaders for standard benchmark datasets (CUB200, CARS196, Stanford Online Product) used to evaluate image retrieval and similarity learning models.
Frequently asked
- What is Confusezius/Deep-Metric-Learning-Baselines?
- A PyTorch pipeline implementing deep metric learning methods including triplet loss, margin loss, and proxy-based losses for image similarity tasks.
- Is Deep-Metric-Learning-Baselines open source?
- Yes — Confusezius/Deep-Metric-Learning-Baselines is open source, released under the Apache-2.0 license.
- What language is Deep-Metric-Learning-Baselines written in?
- Confusezius/Deep-Metric-Learning-Baselines is primarily written in Python.
- How popular is Deep-Metric-Learning-Baselines?
- Confusezius/Deep-Metric-Learning-Baselines has 576 stars on GitHub.
- Where can I find Deep-Metric-Learning-Baselines?
- Confusezius/Deep-Metric-Learning-Baselines is on GitHub at https://github.com/Confusezius/Deep-Metric-Learning-Baselines.