adambielski/siamese-triplet

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

3174 stars · 629 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A PyTorch library implementing siamese and triplet networks for learning image embeddings, with online pair/triplet mining strategies. It provides dataset wrappers, network architectures, loss functions, and selectors for hard negative mining.

Use cases

• train siamese networks for image similarity in pytorch
• learn embeddings with triplet loss and online mining
• implement contrastive loss for metric learning
• few-shot learning feature embeddings
• hard negative pair and triplet mining in minibatches

When to choose

• you need reference implementations of siamese/triplet learning in PyTorch
• you want online hard negative mining strategies for embedding training
• you're learning metric learning concepts with runnable MNIST examples

When to avoid

• you need a maintained library compatible with recent PyTorch versions
• you want production-grade metric learning with broad dataset support
• you need text or multimodal embeddings rather than image-based ones

Facets

library · maturity maintenance

machine-learning deep-learning machine-learning deep-learning image-processing python pytorch siamese-network triplet-loss contrastive-loss metric-learning embeddings online-mining mnist

Member repositories

For agents

markdown · JSON · MCP: product_card(name="adambielski/siamese-triplet")