• 等级
  • 908495 访问
  • 293 原创
  • 16 转发
  • 2513 排名
  • 241 评论
  • 247 获赞

ubuntu16.0.4 opencv4.0.0 GPU 版本的 SURF

opencv4.0.0自带的samplesGPUsurf_keypoint_matcher.cppsurf_keypoint_matcher.cpp#include<iostream>#include"opencv2/opencv_modules.hpp"#ifdefHAVE_OPENCV_XFEATURES2D#include"opencv2/c...

2018-12-21 15:06:52

ubuntu16.0.4 opencv4.0.0 yolov3测试

https://github.com/spmallick/learnopencv/tree/master/ObjectDetection-YOLO硬件信息8Intel®Core™i7-4790CPU@3.60GHz每张图像检测时间约280msopencv中的GPU目前只支持intelGPUyolov3.cpp//Thiscodeiswrittenat...

2018-12-21 14:22:02

ubuntu 16.0.4 opencv 4.0.0 + opencv_contrib 4.0.0 cmake-gui 安装

下载和添加依赖包1、首先更新apt-get,在安装前最好先更新一下系统,不然有可能会安装失败。在终端输入:sudoapt-getupdatesudoapt-getupgrade2、接着安装官方给的opencv依赖包,在终端输入:sudoapt-getinstallbuild-essentialsudoapt-getinstallcmakegitlibgtk2...

2018-12-21 10:28:02

ubuntu 16.0.4 opencv 3.4.1 + opencv_contrib 3.4.1 cmake-gui 安装

下载安装包:opencv3.4.3Sourcecode(zip)https://github.com/opencv/opencv/releasesopencv_contrib3.4.3https://github.com/opencv/opencv_contrib/releases3.4.3.zip解压两个压缩包,然后将opencv_contrib放到ope...

2018-12-17 16:22:29

Ubuntu创建opencv工程并显示一张图片

https://blog.csdn.net/qq_30155503/article/details/79434863 基于上篇已安装好opencv库,现在开始创建第一个opencv工程,并编写显示图片的代码。一、创建工程目录,并进入目录  $mkdirexample &

2018-12-13 14:40:48

ubuntu16.04 opencv多版本管理与切换

https://blog.csdn.net/u012986684/article/details/77490824大家好,今天说说,OpenCV的多版本切换问题!其实总的来说很简单,说下方法!1首先当然准备两个不同版本opencv(比如2.4.9和3.1.0)2cmake-gui设置CMAKE_INSTALL_PREFIX2.4.9安装路径:/usr/local/opencv...

2018-12-10 15:39:33

图像拼接--Fish-Eye Lenses-Based Camera Calibration and Panoramic Image Stitching

Fish-EyeLenses-BasedCameraCalibrationandPanoramicImageStitching2018IEEEInternationalConferenceonConsumerElectronics-Taiwan(ICCE-TW)https://ieeexplore.ieee.org/abstract/document/8448987...

2018-12-06 15:51:23

图像拼接--Bird’s-Eye View Vision System for Vehicle Surrounding Monitoring

Bird’s-EyeViewVisionSystemforVehicleSurroundingMonitoringLiuYC.,LinKY.,ChenYS.(2008)Bird’s-EyeViewVisionSystemforVehicleSurroundingMonitoring.In:SommerG.,KletteR.(eds)Robo...

2018-12-05 15:46:38

Image Stitching 代码

https://github.com/kushalvyas/Python-Multiple-Image-Stitchinghttps://github.com/AmazingZhen/ImageStitchinghttps://github.com/yihui-he/panoramahttps://github.com/nothinglo/NISwGSPhttps://github.com...

2018-12-05 14:12:04

Tensorflow 源码安装成功,导入报错 ImportError: cannot import name 'build_info'

ImportError:cannotimportname‘build_info’ImportError:Couldnotimporttensorflow.Donotimporttensorflowfromitssourcedirectory;changedirectorytooutsidetheTensorFlowsourcetree,andr...

2018-12-04 08:50:56

CNN模型 int8量化实现方式(二)

这里介绍一个完全基于Tensorflow的模型量化方法,以yolov3为例1)利用现有yolov3模型生成Tensorflowpb模型基于https://github.com/mystic123/tensorflow-yolo-v3Runpython./convert_weights.pyandpython./convert_weights_pb.py...

2018-12-03 09:09:33

CNN模型 INT8 量化实现方式(一)

当前CNN模型基本都是float32,将其转换为INT8可以降低模型大小,提升速度,精度降低的也不太多。那么在实际中如何实现这个量化了?在网上找到了两种实践方法,这里先介绍其中的一种。这里主要涉及两个问题:1)就是int8量化;2)就是int8模型的使用基于Caffe-Int8-Convert-Tools进行caffe模型转int8量化在NCNN框架上运行https://b...

2018-11-27 11:05:30

Tensorflow mnist 数据集测试代码 + 自己下载数据

https://blog.csdn.net/weixin_39673686/article/details/81068582importtensorflowastffromtensorflow.examples.tutorials.mnistimportinput_data#自己下载MNIST_data数据集,csdn上下载很快mnist_data_folde...

2018-11-21 14:28:54

ubunu16.04 TensorFlow object detection API 应用配置

TensorFlowobjectdetectionAPI应用–配置主要参考:https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.mdhttps://www.cnblogs.com/zongfa/p/9662832.html1)首先下载Tenso...

2018-11-20 16:23:22

ubuntu16.04 cuda9.0 cudnn Tensorflow GPU 1.10.0

Ubuntu14.04升级到Ubuntu16.04查看目前版本lsb_release-aapt-getupdate&&apt-getdist-upgraderebootdo-release-upgradelsb_release-ahttps://blog.csdn.net/qq_35523593/article/details

2018-11-19 14:02:28

ubuntu 14.04 16.04 18.04使用阿里源

https://blog.csdn.net/bin_zhang1/article/details/81008645首先备份一下原来的sources.listcp/etc/apt/sources.list/etc/apt/sources.list.bak然后修改sources.listsudovi/etc/apt/sources.list然后根据你的版本将sources.lis...

2018-11-16 09:21:46

模型加速--Slimmable neural networks

SlimmableneuralnetworksICLR2019Codeandmodelswillbereleased可瘦身的神经网络,针对不同硬件和运行环境,可以快速提供与之相适应的CNN模型来完成任务。硬件配置好的,给一个大模型,硬件配置差的,给一个小点的模型。同一个模型,设置一下参数就可以了Atruntime,thenetworkcanadjustitsw...

2018-11-07 15:40:40

图像拼接--Seam Carving for Content-Aware Image Resizing

SeamCarvingforContent-AwareImageResizing智能图像缩放ACMTransactionsongraphics(TOG).Vol.26.No.3.ACM,2007https://github.com/danasilver/seam-carvinghttps://github.com/vivianhylee/seam-carvin...

2018-11-07 14:42:13

模型加速--CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization

CLIP-Q:DeepNetworkCompressionLearningbyIn-ParallelPruning-QuantizationCVPR2018http://www.sfu.ca/~ftung/裁剪和量化一体化框架本文的思路比较简单,裁剪+量化一体训练模型分三个步骤:1)Clipping裁剪,将网络中的权重系数值接近0的权重全部置零,当然这种置零是临时...

2018-11-05 14:37:42

模型加速--LCNN: Lookup-based Convolutional Neural Network

LCNN:Lookup-basedConvolutionalNeuralNetworkCVPR2017https://github.com/ildoonet/tf-lcnnhttps://github.com/hessamb/lcnn本文使用查表法加速CNN网络训练和计算,可以在嵌入式设备终端进行CNN网络训练本文对每个网络层构建一个字典Dictionary,每个weig...

2018-11-02 16:13:31

博客专家

O天涯海阁O

主要从事图像分析算法设计、深度学习
关注
  • 计算机软件/算法工程师
  • 中国 安徽省 合肥市
奖章
  • 博客专家
  • 专栏达人
  • 持之以恒