PYNing's repositories
TakePhotoX
基于CameraX 实现拍照，二维码扫描，录像
AlexNet
implement AlexNet with C / convolutional nerual network / machine learning / computer vision
android2
《Android Studio开发实战：从零基础到App上线》随书源码（全面添加注释版）
AppleNumericalComputing
Study and Implementations of Numerical Algorithms on Apple M1 and A* Devices
ArmNeonOptimization
Arm neon optimization practice
AutoAWQ
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.
cpufp
A CPU tool for benchmarking the peak of floating points
FasterTransformer
Transformer related optimization, including BERT, GPT
findcontours_c
achieve findcontours function with C language.
flash-attention
Fast and memory-efficient exact attention
incubator-tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
meetup-slides
Place for meetup slides
nanodet
⚡Super fast and lightweight anchor-free object detection model. 🔥Only 1.8mb and run 97FPS on cellphone🔥
oneflow
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
PaddleOCR
Awesome OCR toolkits based on PaddlePaddle （3.5M practical ultra lightweight OCR system, support training and deployment among server, mobile, embedded and IoT devices）
ppl.cv
ppl.cv is a high-performance image processing library of openPPL supporting x86 and cuda platforms.
Reading-Note
PYNing的读书笔记
tensornetwork.org
Source for The Tensor Network open-source review article
TensorRT-Custom-Plugin-Example
Quick and Self-Contained TensorRT Custom Plugin Implementation and Integration
text-generation-inference
Large Language Model Text Generation Inference
vision
Datasets, Transforms and Models specific to Computer Vision
VNN
VNN是由欢聚集团(Joyy Inc.)推出的高性能、轻量级神经网络部署框架。目前已为Hago、VOO、VFly、马克相机等App提供20余种AI能力的支持，覆盖直播、短视频、视频编辑等泛娱乐场景和工程场景