SHshcheklein·Oct 8, 2022Submission
Library for Metric Learning Pipelines
1 points · Open discussionOML-Team
open-metric-learning
Python2022–2022
OML-Team / open-metric-learning
open-metric-learning
Metric learning and retrieval pipelines, models and zoo.
2Distinct people
3Mentions
0Explicit recommenders
1KGitHub stars
What to know before exploring
What it is
Metric learning and retrieval pipelines, models and zoo.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by 3-hour interval3 dated mentions
Observed mentions: 2022-10-06 21:24:46 UTC to 2022-10-08 20:49:56 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Oct 6, 21:00 | 2022-10-06 21:00:00 UTC | 2022-10-07 00:00:00 UTC | 2 | 1 | 1 |
| Oct 7, 00:00 | 2022-10-07 00:00:00 UTC | 2022-10-07 03:00:00 UTC | 0 | 0 | 0 |
| Oct 7, 03:00 | 2022-10-07 03:00:00 UTC | 2022-10-07 06:00:00 UTC | 0 | 0 | 0 |
| Oct 7, 06:00 | 2022-10-07 06:00:00 UTC | 2022-10-07 09:00:00 UTC | 0 | 0 | 0 |
| Oct 7, 09:00 | 2022-10-07 09:00:00 UTC | 2022-10-07 12:00:00 UTC | 0 | 0 | 0 |
| Oct 7, 12:00 | 2022-10-07 12:00:00 UTC | 2022-10-07 15:00:00 UTC | 0 | 0 | 0 |
| Oct 7, 15:00 | 2022-10-07 15:00:00 UTC | 2022-10-07 18:00:00 UTC | 0 | 0 | 0 |
| Oct 7, 18:00 | 2022-10-07 18:00:00 UTC | 2022-10-07 21:00:00 UTC | 0 | 0 | 0 |
| Oct 7, 21:00 | 2022-10-07 21:00:00 UTC | 2022-10-08 00:00:00 UTC | 0 | 0 | 0 |
| Oct 8, 00:00 | 2022-10-08 00:00:00 UTC | 2022-10-08 03:00:00 UTC | 0 | 0 | 0 |
| Oct 8, 03:00 | 2022-10-08 03:00:00 UTC | 2022-10-08 06:00:00 UTC | 0 | 0 | 0 |
| Oct 8, 06:00 | 2022-10-08 06:00:00 UTC | 2022-10-08 09:00:00 UTC | 0 | 0 | 0 |
| Oct 8, 09:00 | 2022-10-08 09:00:00 UTC | 2022-10-08 12:00:00 UTC | 0 | 0 | 0 |
| Oct 8, 12:00 | 2022-10-08 12:00:00 UTC | 2022-10-08 15:00:00 UTC | 0 | 0 | 0 |
| Oct 8, 15:00 | 2022-10-08 15:00:00 UTC | 2022-10-08 18:00:00 UTC | 0 | 0 | 0 |
| Oct 8, 18:00 | 2022-10-08 18:00:00 UTC | 2022-10-08 21:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
3 sourcesWe released an open-source tool for metric learning - OpenMetricLearning
3 points · Open discussionHi everyone! My comrades and I have released the PyTorch-based library for representation learning named OpenMetricLearning. I kindly ask you to support them by putting a star on GitHub: https://github.com/OML-Team/open-metric-learning!
OML is a great choice when you want to extract features from the images for further clustering, searching and so on. OML provides a ready-to-use zoo of the models pre-trained in a Self-Supervised way (CLIP, DINO, MoCo) and the pipeline for training / finetuning models on your data.
The training part is built around different variations of triplet loss with various strategies of sampling batches, mining triplets and using memory banks. The validation part measures retrieval-like metrics when you use a subset of the data as the searching queries and the rest as a searching index (gallery).
You can use OML de
Read the rest
aling with Python objects or as a non-code solution when you only prepare data in the needed format and write the config file.
We support multi-GPU setup, provide a set of examples on public datasets, well-made documentation and FAQ.