thuml/HashNet

Code release for "HashNet: Deep Learning to Hash by Continuation" (ICCV 2017)

49
/ 100
Emerging

This is a codebase for researchers and practitioners working with large image or video datasets who need to efficiently retrieve similar items. It takes raw image or video data and converts it into compact binary codes (hashes) that can be quickly compared. The primary users are machine learning researchers or data scientists focused on large-scale content retrieval or database indexing.

244 stars. No commits in the last 6 months.

Use this if you are a researcher or practitioner in machine learning and need to implement or experiment with a deep learning method for converting high-dimensional data (like images) into binary hash codes for faster similarity search.

Not ideal if you are looking for a ready-to-use application or a low-code tool for general data hashing, as this requires familiarity with deep learning frameworks like Caffe or PyTorch to implement and adapt.

deep-learning-research image-retrieval similarity-search computer-vision database-indexing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

244

Forks

83

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 02, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thuml/HashNet"

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