dz1135508698 Goto Github PK

opencv_tutorials

Opencv4.0 with python (English&中文)， and will keep the update ! 👊

openpose

OpenPose: A Real-Time Multi-Person Keypoint Detection And Multi-Threading C++ Library

openpose-1

OpenPose的简单实现版本，简洁不简单，so easy. 就一个cpp

opt_flow_tv_l1_nn

paddle-lite-demo

lib, demo, model, data

pixelannotationtool

Annotate quickly images.

pkmopticalflow

Interface for OpenCV's TV-L1 Duality Based Approach to Optical Flow. Does some additional tricks to speed up processing, allow for analysis of the spatio-temporal changes in flow, and visualize the results.

preciseroipooling

Precise RoI Pooling with coordinate gradient support, proposed in the paper "Acquisition of Localization Confidence for Accurate Object Detection" (https://arxiv.org/abs/1807.11590).

pseudo-3d-residual-networks

Pseudo-3D Convolutional Residual Networks for Video Representation Learning

python-spider

Python3网络爬虫实战：VIP视频破解助手；GEETEST验证码破解；小说爬取；动漫下载；手机APP爬取；财务报表入库

pytorch-andriod-greatdemo

Do demo app hand by hand.:https://blog.dltech.xyz/post/pytorch-android/

rcnn

R-CNN: Regions with Convolutional Neural Network Features

realtime_multi-person_pose_estimation

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

resnet-18-caffemodel-on-imagenet

ResNet-18 Caffemodel @ilsvrc12 shrt 256 with Top-1 69% Top-5 89%

resnet-protofiles

Caffe Protofiles for MSRA ResNet: train prototxt

resnet_tensorrt

Small wrapper around Keras' Resnets to transform them into quick UFF models that can use Nvidia's Tensorrt

smp_lpr

利用树莓派实现车牌识别，其中借鉴了大神的代码，调用摄像头，实现了车牌识别，设计一款基于树莓派实现车牌识别的智能限高杆。系统可以分为辨识部分和警示部分，辨识部分以树莓派3B+为核心处理器，基于Linux平台，利用激光对准模块来判断车辆是否超出限定高度，若超过则辅以摄像头来作为抓取车辆信息。通过python3.5和OpenCV来对含有车牌信息的图片，进行高斯去噪、灰度化、边缘检测、二值化、闭操作、字符分割、字符识别匹配等一系列图像处理操作最终实现车牌识别这个系统，最后通过串口将车牌信息发送给警示部分，考虑到要提高数据传输之间的可靠性，本系统自定义了串口之间传输的协议帧组。警示部分主要以STC12C5A32S2为处理核心，辅以点阵屏做为警示。单片机在接收到辨识部分发过来的车牌信息之后，将车牌信息显示在点阵屏上面，不断闪烁以警示超高司机注意安全。

srn

Side-output Residual Network for Object Symmetry Detection in the Wild

st-resnet

Code release for "Spatiotemporal Residual Networks for Video Action Recognition", NIPS16 & "Spatiotemporal Multiplier Networks for Video Action Recognition", CVPR17.

study-09-machinelearning-d

**DeepLearning** (CNN, RNN)

technical_book_dl

This note presents in a technical though hopefully pedagogical way the three most common forms of neural network architectures: Feedforward, Convolutional and Recurrent.

temporal-segment-networks

Code & Models for Temporal Segment Networks (TSN) in ECCV 2016

tensorflow

Computation using data flow graphs for scalable machine learning

tensorflow-vgg16-train-and-test

The purpose of this program is for studying. Using tensorflow trains the vgg16 and recognizes only two kinds of picture(cat and dog).

tensorflow-windows-wheel

Tensorflow prebuilt binary for Windows

tensorrt

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

tensorrt-caffe

A demo using tensorRT on NVIDIA Jetson TX2 accelerating the Caffe model of AlexNet.

tensorrt-demo

TensorRT and TensorFlow demo/example (python, jupyter notebook)

tutorials

机器学习相关教程

tv_l1

An adaptation of Johnson's 2012 dynamic programming alg for TV-L1.