imgbeddings
ML-For-Beginners
Our great sponsors
| imgbeddings | ML-For-Beginners | |
|---|---|---|
| 8 | 28 | |
| 122 | 66,908 | |
| - | 3.5% | |
| 0.0 | 7.6 | |
| about 2 years ago | 18 days ago | |
| Python | HTML | |
| MIT License | MIT License |
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.
imgbeddings
- FLaNK Stack Weekly for 20 Nov 2023
-
Content-Based Image Retrieval
Seconding the recommendation of CLIP embeddings, especially compared to image histograms + requiring OpenCV.
I wrote a naive, minimal dependency Python package to calculate image embeddings (https://github.com/minimaxir/imgbeddings) with some lookup demo notebooks and it works well in a pinch, although it's due for an upgrade.
-
How to build a working AI only using synthetic data in just 5 minutes
Normally, this is Hacker News reductiveness, but yes, image classification via CLIP is that easy, especially with Hugging Face's API for it: https://huggingface.co/docs/transformers/model_doc/clip
I created a Python package to generate image embeddings from CLIP's vision model (without requiring a ML framework), and a simple linear classifier on those embeddings does the trick: https://github.com/minimaxir/imgbeddings
- GitHub - minimaxir/imgbeddings: Python package to generate image embeddings with CLIP without PyTorch/TensorFlow
- Show HN: Python package to create image embeddings without PyTorch/TensorFlow
- I've released a Python package which lets you generate vector representations of images clustering/similarity search/classifier building with a twist: neither PyTorch nor TensorFlow is used!
- [P] I've released a Python package which lets you generate vector representations of images with a twist: neither PyTorch nor TensorFlow is used!
- Show HN: Python package to create image embeddings with o PyTorch/TensorFlow
ML-For-Beginners
-
Good coding groups for black women?
- https://github.com/microsoft/ML-For-Beginners
Also check out this list Pitt puts out every year:
- FLaNK Stack Weekly for 20 Nov 2023
- ML for Beginners GitHub
-
is it worth learning NLP without master degree?
I don't recommend just jumping in into natural language processing directly without understanding artificial intelligence theory. I personally recommend for you to start with the basic stuff (regression, classification, and clustering, for example), and then jump into more advanced topics. You already know software developer stuff, so that's a big step already, and it should be easier to understand some concepts. Maybe follow Microsoft's machine learning for beginners curriculum? It looks like a good roadmap overall to not instantly burn out on nlp
- AI i Machine Learning
- I want to learn more about AI and Machine Learning
-
Pocetak ML karijere
https://github.com/microsoft/ML-For-Beginners jel mislis na ovo?
- How could I have known
- GitHub - microsoft/ML-For-Beginners: 12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
- How do I reset my career after already getting my masters?
What are some alternatives?
ai-music - A vanilla Trasformer Decoder music generation model trained on Final Fantasy OST MIDI songs
FLAML - A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
TwoPhotosOnA6x4 - Stitches 2 photos for printing on a 6"x4" photo.
lego-mindstorms - My LEGO MINDSTORMS projects (using set 51515 electronics)
FLaNK-EveryTransitSystem - Every transit system
pycaret - An open-source, low-code machine learning library in Python
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
Data-Science-For-Beginners - 10 Weeks, 20 Lessons, Data Science for All!
screenshot-to-code - Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
pyVHR - Python framework for Virtual Heart Rate
dalle2-in-python - Use DALL·E 2 in Python
S2ML-Art-Generator - Multiple notebooks which allow the use of various machine learning methods to generate or modify multimedia content [Moved to: https://github.com/justin-bennington/S2ML-Generators]