OliverRensu/D-iGPT

[ICML 2024] This repository includes the official implementation of our paper "Rejuvenating image-GPT as Strong Visual Representation Learners"

27
/ 100
Experimental

This project offers a way for machine learning researchers and engineers to pre-train advanced image recognition models more effectively. By feeding in raw image data, it outputs highly capable visual representation models that excel at understanding image content. The end-user is a machine learning practitioner focused on computer vision tasks who needs state-of-the-art performance.

No commits in the last 6 months.

Use this if you are developing computer vision applications and need to pre-train powerful image recognition models that offer strong performance on classification and segmentation tasks.

Not ideal if you are looking for an out-of-the-box solution for a specific computer vision problem without needing to train custom models or if you are not familiar with deep learning model pre-training workflows.

computer-vision image-recognition deep-learning-research model-pretraining semantic-segmentation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

99

Forks

7

Language

Python

License

Last pushed

May 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/OliverRensu/D-iGPT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.