Stars
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Open-source simulator for autonomous driving research.
Unsupervised text tokenizer for Neural Network-based text generation.
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
Android Live Demo inferenece of Yolov7 using ncnn
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
An awesome list of self-driving cars
A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles
Collection of SOTA efficient computer vision models for embedded applications, with pre-trained weights and training recipes
Built a real-time lane departure warning system with a monocular camera, using OpenCV.
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
Inpaint anything using Segment Anything and inpainting models.
OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Visualizer for neural network, deep learning and machine learning models
NVIDIA GPU tools - monitoring on CLI & web app with multiple agents
PyTorch reimplementation of RegNet (Design Space Design, CVPR2020) on CIFAR10 and ImageNet
Simple bash script to automate the transform images from the Kodak PIXPRO SP360 into an equirectangular format that is understood by https://pannellum.org/
Video solution for sport analysis. Capture, inspect, compare, annotate and measure technical performances.
Fisheye Image to Hemi-Cylinder Correction Tool