Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.

nanoGPT style version of Llama 3.1

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Official Implementation of weights2weights

Python library for YOLOv8 and YOLOv9 small object detection and instance segmentation

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

Utilities intended for use with Llama models.

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

SOTA Semantic Segmentation Models in PyTorch

[ECCV 2024] Embodied Understanding of Driving Scenarios

Official implementation of OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion

Awesome-LLM: a curated list of Large Language Model

Octree-based Sparse Convolutional Neural Networks

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

COCO to YOLO converter

Upgraded repo includes more capabilities, converted the cmd .py scripts to function more intuitively, added 147 different depth output colour map methods, introduced batch image as well as video pr…

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

YOLO-World + EfficientViT SAM

Real-time and accurate open-vocabulary end-to-end object detection

Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX.

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

Training YOLOv9 for face detection on the WIDER Face dataset

Code release for "Segment Anything without Supervision"

fast-stable-diffusion + DreamBooth

[ICCV 2023] Official implementation of the paper "Detection Transformer with Stable Matching"

4M: Massively Multimodal Masked Modeling

RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)

TensorRT implementation of Depth-Anything V1, V2

Integration of YOLOv9 with ByteTracker