lunar-r Goto Github PK

tools-to-design-or-visualize-architecture-of-neural-network

Tools to Design or Visualize Architecture of Neural Network

tracking-python3

In this repository I will give some implementation of single and multiple object tracking algorithms. These include meanShift, CamShift, Boosting, MIL, KCF, TLD , GoTurn, and MedianFlow. Additionally I will show you how to grab frames at a very high FPS from camera and videos.

triplet-loss-gluon

MXNet / Gluon 中 Triplet Loss 算法

triplet-loss-mnist

Triplet Loss 损失函数

turingwechatgroups

10个方向的图灵微信技术群相关事宜

ultimate-python

Ultimate Python study guide for newcomers and professionals alike. :snake: :snake: :snake:

video-stream-face-recognition

visual_tracking_api

A simple visual tracking interface using Python

wireshark

Read-only mirror of Wireshark's Git repository. GitHub won't let us disable pull requests. ☞ THEY WILL BE IGNORED HERE ☜ Please upload them at https://code.wireshark.org/review/ .

workingtime

yiyi_mtcnn_keras

MTCNN提出了一种Multi-task的人脸检测框架，将人脸检测和人脸特征点检测同时进行。提出一个新的基于CNN的级联型框架，用于联和（joint）人脸检测和对齐；还设计轻量级的CNN架构使得速度上可以达到实时；提出一个有效的online hard sample mining方法来提高表现能力；在人脸检测和人脸对齐上提高了不少精度。论文原文采用caffe实现，本项目用keras/tensorflow+python实现。

yolo-lite

All the trained models used while developing YOLO-LITE

yolo_facedetection

使用YoloV3来实现人脸检测(A face detection demo used YoloV3)

yolov3-based-face-detection-tracking

This is a robot project for television live. System will tracking the host's face, making the face in the middle of the screen. Main algorithm is Yolov3, trained on WIDER FACE and tested on FDDB benchmark. Extremely fine performance!

yolov3-model-pruning

对 YOLOv3 做模型剪枝，在 oxford hand 数据集上模型的参数量减少 80% ，FLOPs 降低 70%，Infer 的速度可以达到原来的 200%，mAP 基本保持不变

zhihu_article

zihaotutorialofraspberrypi

子豪兄的零基础树莓派教程，代码存放地及更新勘误

zju-icicles

浙江大学课程攻略共享计划