Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding

深度学习思想越来越火，在今年的CVPR 2015 文章中相关文章就有20多篇，可见是非常火的。最近在做关于语义分割和场景解析的内容，看到这篇文章后也是非常高兴。

CN24 is a complete semantic segmentation framework using fully convolutional networks. It supports a wide variety of platforms (Linux, Mac OS X and Windows) and libraries (OpenCL, Intel MKL, AMD ACML...) while providing dependency-free reference implementations. The software is developed at the Computer Vision Group, University of Jena.

文章说可以在Windows、Mac和Linux系统上很好的运行，又可以支持OpenCL、Intel MKL , AMD ACML 来并行计算加速，看起来还真不错！

官方源码地址：

[ CN24 ]

接下来先上实验结果：

实验环境[ubuntu 15.04]，暂时没有用GPU加速

代码程序目录：

执行后的结果:

单张图片测试结果，左侧是语义分割后的结果，右侧是真实的测试图。

没有用GPU加速，果然处理一张图片还是挺慢的，耗时还是挺多的，如下图所示：

下面就是摸索代码，下一节会继续分享学习过程，谢谢！

时间： 2024-10-11 21:26:08

Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding的相关文章

（转）A Beginner's Guide To Understanding Convolutional Neural Networks

Adit Deshpande CS Undergrad at UCLA ('19) Blog About A Beginner's Guide To Understanding Convolutional Neural Networks Introduction Convolutional neural networks. Sounds like a weird combination of biology and math with a little CS sprinkled in, but

卷积神经网络用于视觉识别Convolutional Neural Networks for Visual Recognition

Table of Contents: Architecture Overview ConvNet Layers Convolutional Layer Pooling Layer Normalization Layer Fully-Connected Layer Converting Fully-Connected Layers to Convolutional Layers ConvNet Architectures Layer Patterns Layer Sizing Patterns C

A Beginner's Guide To Understanding Convolutional Neural Networks(转)

A Beginner's Guide To Understanding Convolutional Neural Networks Introduction Convolutional neural networks. Sounds like a weird combination of biology and math with a little CS sprinkled in, but these networks have been some of the most influential

【论文翻译】MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications 论文链接:https://arxiv.org/pdf/1704.04861.pdf 摘要和Prior Work就略了,懒. 1. Introduction 介绍了一种高效的网络架构和两个超参数,以便构建非常小的,低延迟(快速度)的模型,可以轻松匹配移动和嵌入式视觉应用的设计要求.引入的两个简单的全局超参数,使得模型可以在速度和准确度

Learning to Compare Image Patches via Convolutional Neural Networks --- Reading Summary

Learning to Compare Image Patches via Convolutional Neural Networks --- Reading Summary 2017.03.08 Target: this paper attempt to learn a geneal similarity function for comparing image patches from image data directly. There are several ways in which

（转）A Beginner's Guide To Understanding Convolutional Neural Networks Part 2

Adit Deshpande CS Undergrad at UCLA ('19) Blog About A Beginner's Guide To Understanding Convolutional Neural Networks Part 2 Introduction Link to Part 1 In this post, we’ll go into a lot more of the specifics of ConvNets. Disclaimer: Now, I do reali

Convolutional Neural Networks (CNNs / ConvNets) Notes

Convolutional Neural Networks Convolutional Neural Networks are made up of neurons that have learnable weights and biases. Each neuron receives some inputs, performs a dot product and optionally follows it with a non-linearity. They still have a loss

Convolutional Neural Networks for Visual Recognition 8

Convolutional Neural Networks (CNNs / ConvNets) 前面做了如此漫长的铺垫,如今终于来到了课程的重点. Convolutional Neural Networks. 简称CNN,与之前介绍的一般的神经网络相似,CNN相同是由能够学习的权值与偏移量构成.每个神经元接收一些输入.做点积运算加上偏移量,然后选择性的通过一些非线性函数.整个网络终于还是表示成一个可导的loss function,网络的起始端是输入图像.网络的终端是每一类的预測值,通过一个ful

Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks

一.主要思想 CNN在计算机视觉领域取得了非常优异的成绩,但是训练CNN的模型需要大量的数据,小数据集上面无法体现出出CNN的优势.针对这个问题作者提出了通过Transferring CNN weights来解决这个问题.首先在imagenet等大数据集上面训练传统的CNN模型,然后在针对特定的任务就行fine-tuning(可能不准确),但是和以往fine-tuning不同的是:改变了整个pre-training的CNN的框架,在VOC2007和VOC2012上面取得了很好的结果. 二.基本框