megadetector-gui
Typesense
megadetector-gui | Typesense | |
---|---|---|
3 | 131 | |
41 | 17,965 | |
- | 2.7% | |
0.0 | 9.8 | |
over 1 year ago | 9 days ago | |
JavaScript | C++ | |
- | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
megadetector-gui
-
Ask HN: What not-profit-seeking project are you tinkering with this week?
On (some) weekends I work on Megadetector GUI [0]. Megadetector [1] is an object detection model trained on millions of camera trap images and is widely used by conservationists. The issue is that it's rather technical to set up, so I made a GUI for it.
Currently working on a brand new version (not public just yet) that will use the latest MD version (v5 is way faster), better UI and most importantly GPU support out of the box.
[0] https://github.com/petargyurov/megadetector-gui
[1] https://github.com/microsoft/CameraTraps/blob/main/megadetec...
-
Ask HN: Who Wants to Collaborate?
> ML to identify gorillas by their unique nose prints
Really cool stuff. I wonder if face detection is sufficient too? It has been proven to work for brown bears [0].
I have also been doing some open source work [1] to democratise object detection in this space but I haven't had the time to make improvements to the project in a while.
* [0] http://bearresearch.org/
* [1] https://github.com/petargyurov/megadetector-gui
-
Kea parrots perform domain-general statistical inference
In case any camera trap folk are here, I'm currently volunteering with the NZ Department of Conservation to build an AI-assisted image sorting tool that speeds up the weeding out of empty images.
https://github.com/petargyurov/megadetector-gui
This currently used to assist the conservation efforts of various endemic species such as the kakapo, kea and takahe. (The ML model used is not limited to just these species!)
Typesense
-
FlowDiver: The Road to SSR - Part 1
Disregarding props-drilling technique in favor of a more reliable and elegant solution we looked for inspiration elsewhere. Another project of ours .find was using Typesense/Algolia components, which looked a bit like black-box/magic, but at the same time provided a clean approach to build complex and highly customizable solutions.
-
Release Radar · April 2024 Edition: Major updates from the open source community
Have you ever tried to look up something, only to realise your search engine doesn't recognise your typos? Typesense to the rescue! It's a fast, typo-tolerant search engine built for an easier browsing experience. The latest version comes with new features such as built-in conversational search, image search, voice search, analytics, and more. Dive into the release notes for the full list of changes and enhancements.
-
Website Search Hurts My Feelings
There are actually plenty of non-ES products that are way easier to integrate and tune (and get better results with less effort).
- Typesense (https://github.com/typesense/typesense)
- Algolia
- Google Programmable Search Engine (https://programmablesearchengine.google.com/about/)
- Remote Machine Learning and Searching on a Raspberry Pi 5
-
Open Source alternatives to tools you Pay for
Typesense - Open Source Alternative to Algolia
-
DNS record "hn.algolia.com" is gone
If you like your penny take a look at Typesense https://typesense.org/ - nothing to complain here. Especially nothing complain about pricing.
-
Vector databases: analyzing the trade-offs
I work on Typesense [1] (historically considered an open source alternative to Algolia).
We then launched vector search in Jan 2023, and just last week we launched the ability to generate embeddings from within Typesense.
You'd just need to send JSON data, and Typesense can generate embeddings for your data using OpenAI, PaLM API, or built-in models like S-BERT, E-5, etc (running on a GPU if you prefer) [2]
You can then do a hybrid (keyword + semantic) search by just sending the search keywords to Typesense, and Typesense will automatically generate embeddings for you internally and return a ranked list of keyword results weaved with semantic results (using Rank Fusion).
You can also combine filtering, faceting, typo tolerance, etc - the things Typesense already had.
[1] https://github.com/typesense/typesense
[2] https://typesense.org/docs/0.25.0/api/vector-search.html
-
Creating an advanced search engine with PostgreSQL
For something small with a minimal footprint, I'd recommend Typesense. https://github.com/typesense/typesense
-
Obsidian Publish full text search
I haven’t used Publish, but I’d assume you could use something like https://typesense.org/ to index and search the vault.
-
DynamoDB search options
A cheaper option would be to use https://typesense.org. You can use DynamoDb streams to automatically load records. It has worked well for me.
What are some alternatives?
futurecoder - 100% free and interactive Python course for beginners
MeiliSearch - A lightning-fast search API that fits effortlessly into your apps, websites, and workflow
HPI - Human Programming Interface 🧑👽🤖
Elasticsearch - Free and Open, Distributed, RESTful Search Engine
mnm - mnm implements TMTP protocol. Let Internet sites message members directly, instead of unreliable, insecure email. Contributors welcome! (Server)
Apache Solr - Apache Lucene and Solr open-source search software
schemats - A postgres & mysql -> typescript interface generator
meilisearch-laravel-scout - MeiliSearch integration for Laravel Scout
CameraTraps - PyTorch Wildlife: a Collaborative Deep Learning Framework for Conservation.
loki - Like Prometheus, but for logs.
SpeechLoop - Many ASRs under one roof. With Benchmarking... answering the question. What is the best ASR for my dataset?
sonic - 🦔 Fast, lightweight & schema-less search backend. An alternative to Elasticsearch that runs on a few MBs of RAM.