lofyol

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

vision

Datasets, Transforms and Models specific to Computer Vision

DeepStream-Yolo-Pose

NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 application for YOLO-Pose models

CV-CUDA

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

pycuda

CUDA integration for Python, plus shiny features

CUDA-FastBEV

TensorRT deploy and PTQ/QAT tools development for FastBEV, total time only need 6.9ms!!!

pygubu

A simple GUI builder for the python tkinter module

tkinter-helper

为tkinter打造的可视化拖拽布局界面设计小工具

Tkinter-Designer

An easy and fast way to create a Python GUI 🐍

pyobfuscate

pyobfuscate

Torch-Pruning

[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs

cv_note

记录cv算法工程师的成长之路，分享计算机视觉和模型压缩部署技术栈笔记。https://harleyszhang.github.io/cv_note/

pandora

潘多拉，一个让你呼吸顺畅的ChatGPT。Pandora, a ChatGPT that helps you breathe smoothly.

Detic-onnxrun-cpp-py

使用ONNXRuntime部署Detic检测2万1千种类别的物体，包含C++和Python两个版本的程序

TensorRT_Inference_Demo

A repo that uses TensorRT to deploy wll-trained models.Support RTDETR,YOLO-NAS,YOLOV5,YOLOV6,YOLOV7,YOLOV8,YOLOX.

YOLOv8-TensorRT-CPP

YOLOv8 TensorRT C++ Implementation

TensorRT_Tutorial

multiyolov5

joint detection and semantic segmentation, based on ultralytics/yolov5,

30-seconds-of-code

Short code snippets for all your development needs

FaceRecognitionCpp

Real Time Face Recognition using MTCNN for detecting and Arcface for generating feature. Over 50FPS on CPU!

ppl.nn

A primitive library for neural network

segment-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.

visdom

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

ppl.cv

ppl.cv is a high-performance image processing library of openPPL supporting various platforms.

MQBench

Model Quantization Benchmark

libfacedetection

An open source library for face detection in images. The face detection speed can reach 1000FPS.

ppq

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

YOLOv8-TensorRT

YOLOv8 using TensorRT accelerate !

tensorflow-onnx

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

pytorch-lightning

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.