minimaxir/imgbeddings
Python package to generate image embeddings with CLIP without PyTorch/TensorFlow
This tool helps data scientists and machine learning engineers analyze large collections of images. You input individual images or batches of image files, and it generates numerical representations (embeddings) for each. These embeddings can then be used for tasks like grouping similar images, finding specific images within a dataset, or preparing images for classification models.
161 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to transform images into numerical data for machine learning tasks like clustering, similarity search, or building image classifiers, especially when performance and efficiency are important.
Not ideal if your workflow requires linking image and text data directly within the embedding generation process, as this tool focuses solely on image-to-embedding conversion.
Stars
161
Forks
15
Language
Python
License
MIT
Category
Last pushed
Mar 28, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/minimaxir/imgbeddings"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FlagOpen/FlagEmbedding
Retrieval and Retrieval-augmented LLMs
qdrant/fastembed
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Blaizzy/mlx-embeddings
MLX-Embeddings is the best package for running Vision and Language Embedding models locally on...
Merck/Sapiens
Sapiens is a human antibody language model based on BERT.
amansrivastava17/embedding-as-service
One-Stop Solution to encode sentence to fixed length vectors from various embedding techniques