YOLO-World
mwmbl
YOLO-World | mwmbl | |
---|---|---|
3 | 27 | |
3,442 | 1,370 | |
13.4% | 1.6% | |
9.0 | 9.4 | |
6 days ago | 5 days ago | |
Python | Python | |
GNU General Public License v3.0 only | GNU Affero General Public License v3.0 |
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.
YOLO-World
-
A History of CLIP Model Training Data Advances
2024 is shaping up to be the year of multimodal machine learning. From real-time text-to-image models and open-world vocabulary models to multimodal large language models like GPT-4V and Gemini Pro Vision, AI is primed for an unprecedented array of interactive multimodal applications and experiences.
- FLaNK Stack Weekly 19 Feb 2024
-
Making My Bookshelves Clickable
Post author here. I like this idea. I plan to explore it and make a more generic solution. I'd love to have a point-and-click interface for annotating scenes.
For example, I'd like to be able to click on pieces of coffee equipment in a photo of my coffee setup so I can add sticky note annotations when you hover over each item.
For the bookshelves idea specifically, I would love to have a correction system in place. The problem isn't so much SAM as it is Grounding DINO, the model I'm using for object identification. I then pass each identified region to SAM and map the segmentation mask to the box.
Grounding DINO detects a lot of book spines, but often misses 1-2. I am planning to try out YOLO-World (https://github.com/AILab-CVC/YOLO-World), which, in my limited testing, performs better for this task.
mwmbl
- FLaNK Stack Weekly 19 Feb 2024
-
Text Processing Practice Expt: 27 SERP Types to SQLite (Yy084)
echo "https://mwmbl.org/?q=$x"|client 185.34.32.175
-
How bad are search results? Compare Google, Bing, Marginalia, Kagi, and ChatGPT
Ironically I had to use a search engine to discover what "Mwmbl" was. It's apparently a search engine. But, visiting the front page, I see something akin to a git commit log?! I'm not sure I'd have guessed that this was a SE if Brave Search did not tell me it was (even then I'm not convinced yet).
https://mwmbl.org/
-
Indexing a Billion Pages
I believe this is closer to the thing you were asking about, and the simple answer appears to be "a home grown one in python" https://github.com/mwmbl/mwmbl/blob/e544d45c374c13cdc1a5048d...
- Welcome to mwmbl, the free, open-source and non-profit search engine
- Marginalia.nu API
- Show HN: Ichido, search engine that tags sites using Google and Cloudflare
- Introduction!
- Mwmbl, the free, open-source and non-profit search engine
What are some alternatives?
Lobsters - Computing-focused community centered around link aggregation and discussion
whoogle-search - A self-hosted, ad-free, privacy-respecting metasearch engine
PiTheremin
code-search-blocklist - A list of domains hosting scrapped code snippets and polluting search results to block.
ublock-origin-shitty-copies-filter - Filter for DuckDuckGo and Google to remove those spam-websites that just blatantly copy and paste content from well known websites.
ublacklist - Blocks specific sites from appearing in Google search results
bertsearch - Elasticsearch with BERT for advanced document search.
searx - Privacy-respecting metasearch engine [Moved to: https://github.com/searx/searx]
MarginaliaSearch - Internet search engine for text-oriented websites. Indexing the small, old and weird web.
config-files - My collection of .dotfiles, settings and snippets.
bingo - The missing package manager for golang binaries (its homebrew for "go install")
Yacy - Distributed Peer-to-Peer Web Search Engine and Intranet Search Appliance