perfyperfect Goto Github PK

paddlepaddle-deepspeech

基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。

paddleseg

End-to-end image segmentation kit based on PaddlePaddle.

pfld_106_face_landmarks

106点人脸关键点检测的PFLD算法实现

pipnet

Efficient facial landmark detector

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

qrcode-ncnn

QRCode(from WeChat) implement in ncnn⚡二维码检测&解码⚡ncnn⚡

realsr-ncnn-vulkan

realsr converter ncnn version, runs fast on intel / amd / nvidia GPU with vulkan

rrcf

🌲 Implementation of the Robust Random Cut Forest algorithm for anomaly detection on streams

scv

Learning Optical Flow from a Few Matches (CVPR 2021)

server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

shawn_pose_estimation_by_opencv

This is my initial experiments on pose estimation using opencv.More details:http://www.cnblogs.com/singlex/p/pose_estimation_0.html

simd

C++ image processing and machine learning library with using of SIMD: SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, AVX2, AVX-512, VMX(Altivec) and VSX(Power7), NEON for ARM.

skt

SKT distillation (ACM MM 2020)

solo

SOLO: Segmenting Objects by Locations https://arxiv.org/abs/1912.04488

stable-diffusion-ncnn

Stable Diffusion in NCNN with c++

tensorrtx

Implementation of popular deep learning networks with TensorRT network definition API

textboxes_plusplus

TextBoxes++: A Single-Shot Oriented Scene Text Detector

tiny-cuda-nn

Lightning fast & tiny C++/CUDA neural network framework

tiny-tensorrt

a simple, efficient, easy-to-use nvidia TensorRT wrapper for cnn,sopport c++ and python

tnn

TNN：移动端高性能、轻量级推断框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推断框架进一步完善。

ultra-fast-lane-detection

Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

van-classification

vcn

Volumetric Correspondence Networks for Optical Flow, NeurIPS 2019.

video-to-pose3d

Convert video to 3D pose in one-key.

videox

VideoX: a collection of video cross-modal models

wenetspeech

A 10000+ hours dataset for Chinese speech recognition

white-box-cartoonization

Official tensorflow implementation for CVPR2020 paper “Learning to Cartoonize Using White-box Cartoon Representations”

yolact

A simple, fully convolutional model for real-time instance segmentation.

yolo-fastest

:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB

yolo-v5

:art: Pytorch YOLO v5 训练自己的数据集超详细教程！！！ :art: (提供PDF训练教程下载）