l1129433134 Goto Github PK

cplusplus_sdk

腾讯优图开放平台 c++ sdk

cpu-cache

deep-learning

:computer:深度学习实战：手写数字识别、Discuz验证码识别、垃圾分类、语义分割

deep-learning-with-tensorflow-book

深度学习开源书，基于TensorFlow 2.0实战。Open source Deep Learning book, based on TensorFlow 2.0 framework.

deepcompression-caffe

Caffe for Deep Compression

deepcore

一款基于CUDA的针对NVIDIA的GPU进行了深度优化的深度学习底层核心计算库，在相同的算法下矩阵乘法和卷积的性能同于甚至大于最新版本的cudnn,该项目仍在持续开发中！

deeplearningtutorials-1

Deep Learning与PyTorch入门实战视频教程

deepmon

demo-js-danmu

一个用WildDog实现的弹幕示例

densepose-api

DensePose in a GPU enabled Docker API

depthwiseconvolution

A personal depthwise convolution layer implementation on caffe by liuhao.(only GPU)

dnnlibrary

Daquexian's NNAPI Library. Run neural network using the new NNAPI on Android !

dynet

DyNet: The Dynamic Neural Network Toolkit

easy3d

A lightweight, easy-to-use, and efficient C++ library for processing and rendering 3D data

easyobj

3D model viewer. (soft renderer) - OBJ模型查看器（软渲染）

easyopenpose

OpenPose的简单实现

easyplayer

SDK：RTSP Player播放器，支持多平台：Windows、Android、IOS(开发中)

easyquant

EasyQuant(EQ) is an efficient and simple post-training quantization method via effectively optimizing the scales of weights and activations.

efficient_quadtree

Poisson blending job used quadtree to accelerate.

eos

A lightweight 3D Morphable Face Model fitting library in modern C++14

face-alignment

:fire: 2D and 3D Face alignment library build using pytorch

face-detection-opencv-api

An API to detect faces built via. OpenCV deployed using Django

face-landmark-android

Android AR Camera

face-marks

Detect facial landmarks with TensorFlow and CoreML on iPhone.

face-parsing.pytorch

Using modified BiSeNet for face parsing in PyTorch

face-recognition-api-django

Running Django server

face3d

Python tools for 3D face: 3DMM, Mesh processing(transform, camera, light, render), 3D face representations.

faceac

人脸识别扫描（活体检测功能，眨眼、摇头、点头），身份证认证

facecapture

an Android app kind like Facerig(but simpler)

faceconverter

Face swap and 3D alignment from a single image based on PRNet