[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
- object-detection
- open-world
- open-world-detection
- vision-language
47,133 repositories indexed
265–288 of 1,482 · Most stars
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Simple job queues for Python
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Python bindings for llama.cpp
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Library for building powerful interactive command line applications in Python
Hackable and optimized Transformers building blocks, supporting a composable construction.
Polar — A billing platform for the intelligence era
Modin: Scale your Pandas workflows by changing a single line of code
q - Run SQL directly on delimited files and multi-file sqlite databases
Build, Manage and Deploy AI/ML Systems
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
Implementation of Nougat Neural Optical Understanding for Academic Documents
A modular SQL linter and auto-formatter with support for multiple dialects and templated code.
The leading native Python SSHv2 protocol library.
the LLM vulnerability scanner
Manipulate audio with a simple and easy high level interface
A terminal spreadsheet multitool for discovering and arranging data
Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos.
💨 Fast, Async-ready, Openapi, type hints based framework for building APIs
Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported