Guillem96/data2vec-vision
PyTorch implementation of Data2Vec self-supervised approach for vision use cases.
This project helps machine learning engineers build powerful computer vision models for tasks like image recognition or object detection, even with limited labeled data. It takes a collection of images and outputs a trained model that can extract meaningful features from new images. This is for machine learning engineers who want to pre-train image understanding models more efficiently.
No commits in the last 6 months.
Use this if you need to train a robust image feature extractor or image understanding model without relying on massive amounts of manually labeled data.
Not ideal if you're looking for a ready-to-use model with pre-trained weights for large-scale production use, as this project focuses on providing the implementation for training.
Stars
18
Forks
5
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Oct 07, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Guillem96/data2vec-vision"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kermitt2/delft
a Deep Learning Framework for Text https://delft.readthedocs.io/
yoeo/guesslang
Detect the programming language of a source code
matthewdeanmartin/whats_that_code
detect programming language of source in pure python from an ensemble of classifiers
airalcorn2/Deep-Semantic-Similarity-Model
My Keras implementation of the Deep Semantic Similarity Model (DSSM)/Convolutional Latent...
christiansafka/img2vec
:fire: Use pre-trained models in PyTorch to extract vector embeddings for any image