Explore Projects
Discover 32 open source projects
Showing 1-20 of 32 projects
open-mmlab/mmdetection
Object detection toolbox for PyTorch with support for multiple tasks and state-of-the-art models.
lukas-blecher/LaTeX-OCR
A deep learning model that converts images of mathematical equations into LaTeX code.
jacobgil/pytorch-grad-cam
Advanced AI Explainability library for computer vision models built with PyTorch.
NielsRogge/Transformers-Tutorials
This repository contains demos for the Transformers library by HuggingFace, a popular NLP and computer vision library.
FoundationVision/VAR
An ultra-simple, state-of-the-art codebase for autoregressive image generation using advanced AI models.
adithya-s-k/omniparse
A Python library for ingesting, parsing, and optimizing any data format for enhanced compatibility with GenAI frameworks.
JingyunLiang/SwinIR
An open-source project that provides a state-of-the-art image restoration model using the Swin Transformer architecture.
huawei-noah/Efficient-AI-Backbones
Efficient AI model backbones developed by Huawei's Noah's Ark Lab, including GhostNet, TNT, and MLP.
open-mmlab/mmpretrain
A pre-training toolbox and benchmark for vision AI models, including self-supervised learning and state-of-the-art architectures.
google-research/scenic
JAX library for computer vision research with transformers, attention mechanisms, and vision models
towhee-io/towhee
A fast and simple framework for building neural data processing pipelines using Python.
mit-han-lab/efficientvit
Efficient vision foundation models for high-resolution generation and perception.
InternLM/InternLM-XComposer
A comprehensive multimodal system for long-term streaming video and audio interactions using large language models.
OpenGVLab/InternVideo
A video foundation model and dataset for multimodal understanding and video understanding tasks.
hila-chefer/Transformer-Explainability
Official PyTorch implementation for a novel method to visualize classifications by Transformer based networks.
ViTAE-Transformer/ViTPose
A simple vision transformer baseline for human pose estimation, with pre-trained models and advanced capabilities.
alibaba/EasyCV
An all-in-one computer vision toolkit for developers building AI-powered applications.
microsoft/Cream
A collection of Microsoft's work on NAS and Vision Transformer for efficient AI models.
MCG-NJU/VideoMAE
A self-supervised video representation learning model for video understanding tasks.
emcf/thepipe
A Python library that helps developers extract structured data from tricky documents using vision-language models.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.