omoindrot/tensorflow-triplet-loss

Implementation of triplet loss in TensorFlow

51
/ 100
Established

Implements online triplet mining with two strategies—"batch all" and "batch hard"—to efficiently select hard and semi-hard triplets during training for metric learning tasks. Includes TensorBoard integration for monitoring triplet quality metrics and demonstrates end-to-end training on MNIST with t-SNE embedding visualization, supporting both CPU and GPU via standard TensorFlow workflows.

1,130 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,130

Forks

280

Language

Python

License

MIT

Last pushed

May 09, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/omoindrot/tensorflow-triplet-loss"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.