cobanov/unlabeled-image-autoencoder
Train an autoencoder for unlabeled image datasets.
This project helps data scientists and machine learning engineers understand the underlying structure of unlabeled image datasets. It takes raw image files as input and processes them to produce a lower-dimensional representation, which can then be visualized to reveal natural groupings or clusters within the images, even without any initial labels.
No commits in the last 6 months.
Use this if you have a collection of images without labels and need to discover hidden patterns, group similar images, or prepare them for further analysis where understanding data relationships is key.
Not ideal if you already have labeled image datasets or if your primary goal is classification rather than exploratory analysis and clustering.
Stars
7
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/cobanov/unlabeled-image-autoencoder"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cosmosgl/graph
GPU-accelerated force graph layout and rendering
Clay-foundation/model
The Clay Foundation Model - An open source AI model and interface for Earth
nomic-ai/nomic
Nomic Developer API SDK
omoindrot/tensorflow-triplet-loss
Implementation of triplet loss in TensorFlow
sashakolpakov/dire-jax
DImensionality REduction in JAX