登录
首页 » Python » Unet-master2

Unet-master2

于 2019-04-19 发布
0 144
下载积分: 1 下载次数: 13

代码说明:

说明:  CN对图像进行像素级的分类,从而解决了语义级别的图像分割(semantic segmentation)问题。与经典的CNN在卷积层之后使用全连接层得到固定长度的特征向量进行分类(全联接层+softmax输出)不同,FCN可以接受任意尺寸的输入图像,采用反卷积层对最后一个卷积层的feature map进行上采样, 使它恢复到输入图像相同的尺寸,从而可以对每个像素都产生了一个预测, 同时保留了原始输入图像中的空间信息, 最后在上采样的特征图上进行逐像素分类。(CN classifies images at the pixel level, thus resolving the problem of semantic segmentation at the semantic level. Unlike classical CNN, which uses full-connection layer to get fixed-length feature vectors after convolution layer for classification (full-connection layer + soft Max output), FCN can accept any size of input image, and uses deconvolution layer to sample feature map of the last convolution layer to restore it to the same size of input image, so that each pixel can be generated. At the same time, the spatial information of the original input image is retained. Finally, the pixel-by-pixel classification is carried out on the feature map sampled above.)

文件列表:

Unet-master, 0 , 2018-04-19
Unet-master\README.md, 141 , 2018-04-19
Unet-master\data.py, 8130 , 2018-04-19
Unet-master\images, 0 , 2018-04-19
Unet-master\images\test, 0 , 2018-04-19
Unet-master\images\test\0.tif, 262278 , 2018-04-19
Unet-master\images\test\1.tif, 262278 , 2018-04-19
Unet-master\images\test\10.tif, 262278 , 2018-04-19
Unet-master\images\test\11.tif, 262278 , 2018-04-19
Unet-master\images\test\12.tif, 262278 , 2018-04-19
Unet-master\images\test\13.tif, 262278 , 2018-04-19
Unet-master\images\test\14.tif, 262278 , 2018-04-19
Unet-master\images\test\15.tif, 262278 , 2018-04-19
Unet-master\images\test\16.tif, 262278 , 2018-04-19
Unet-master\images\test\17.tif, 262278 , 2018-04-19
Unet-master\images\test\18.tif, 262278 , 2018-04-19
Unet-master\images\test\19.tif, 262278 , 2018-04-19
Unet-master\images\test\2.tif, 262278 , 2018-04-19
Unet-master\images\test\20.tif, 262278 , 2018-04-19
Unet-master\images\test\21.tif, 262278 , 2018-04-19
Unet-master\images\test\22.tif, 262278 , 2018-04-19
Unet-master\images\test\23.tif, 262278 , 2018-04-19
Unet-master\images\test\24.tif, 262278 , 2018-04-19
Unet-master\images\test\25.tif, 262278 , 2018-04-19
Unet-master\images\test\26.tif, 262278 , 2018-04-19
Unet-master\images\test\27.tif, 262278 , 2018-04-19
Unet-master\images\test\28.tif, 262278 , 2018-04-19
Unet-master\images\test\29.tif, 262278 , 2018-04-19
Unet-master\images\test\3.tif, 262278 , 2018-04-19
Unet-master\images\test\4.tif, 262278 , 2018-04-19
Unet-master\images\test\5.tif, 262278 , 2018-04-19
Unet-master\images\test\6.tif, 262278 , 2018-04-19
Unet-master\images\test\7.tif, 262278 , 2018-04-19
Unet-master\images\test\8.tif, 262278 , 2018-04-19
Unet-master\images\test\9.tif, 262278 , 2018-04-19
Unet-master\images\train, 0 , 2018-04-19
Unet-master\images\train\images, 0 , 2018-04-19
Unet-master\images\train\images\0.tif, 262278 , 2018-04-19
Unet-master\images\train\images\1.tif, 262278 , 2018-04-19
Unet-master\images\train\images\10.tif, 262278 , 2018-04-19
Unet-master\images\train\images\11.tif, 262278 , 2018-04-19
Unet-master\images\train\images\12.tif, 262278 , 2018-04-19
Unet-master\images\train\images\13.tif, 262278 , 2018-04-19
Unet-master\images\train\images\14.tif, 262278 , 2018-04-19
Unet-master\images\train\images\15.tif, 262278 , 2018-04-19
Unet-master\images\train\images\16.tif, 262278 , 2018-04-19
Unet-master\images\train\images\17.tif, 262278 , 2018-04-19
Unet-master\images\train\images\18.tif, 262278 , 2018-04-19
Unet-master\images\train\images\19.tif, 262278 , 2018-04-19
Unet-master\images\train\images\2.tif, 262278 , 2018-04-19
Unet-master\images\train\images\20.tif, 262278 , 2018-04-19
Unet-master\images\train\images\21.tif, 262278 , 2018-04-19
Unet-master\images\train\images\22.tif, 262278 , 2018-04-19
Unet-master\images\train\images\23.tif, 262278 , 2018-04-19
Unet-master\images\train\images\24.tif, 262278 , 2018-04-19
Unet-master\images\train\images\25.tif, 262278 , 2018-04-19
Unet-master\images\train\images\26.tif, 262278 , 2018-04-19
Unet-master\images\train\images\27.tif, 262278 , 2018-04-19
Unet-master\images\train\images\28.tif, 262278 , 2018-04-19
Unet-master\images\train\images\29.tif, 262278 , 2018-04-19
Unet-master\images\train\images\3.tif, 262278 , 2018-04-19
Unet-master\images\train\images\4.tif, 262278 , 2018-04-19
Unet-master\images\train\images\5.tif, 262278 , 2018-04-19
Unet-master\images\train\images\6.tif, 262278 , 2018-04-19
Unet-master\images\train\images\7.tif, 262278 , 2018-04-19
Unet-master\images\train\images\8.tif, 262278 , 2018-04-19
Unet-master\images\train\images\9.tif, 262278 , 2018-04-19
Unet-master\images\train\label, 0 , 2018-04-19
Unet-master\images\train\label\0.tif, 262278 , 2018-04-19
Unet-master\images\train\label\1.tif, 262278 , 2018-04-19
Unet-master\images\train\label\10.tif, 262278 , 2018-04-19
Unet-master\images\train\label\11.tif, 262278 , 2018-04-19
Unet-master\images\train\label\12.tif, 262278 , 2018-04-19
Unet-master\images\train\label\13.tif, 262278 , 2018-04-19
Unet-master\images\train\label\14.tif, 262278 , 2018-04-19
Unet-master\images\train\label\15.tif, 262278 , 2018-04-19
Unet-master\images\train\label\16.tif, 262278 , 2018-04-19
Unet-master\images\train\label\17.tif, 262278 , 2018-04-19
Unet-master\images\train\label\18.tif, 262278 , 2018-04-19
Unet-master\images\train\label\19.tif, 262278 , 2018-04-19
Unet-master\images\train\label\2.tif, 262278 , 2018-04-19
Unet-master\images\train\label\20.tif, 262278 , 2018-04-19
Unet-master\images\train\label\21.tif, 262278 , 2018-04-19
Unet-master\images\train\label\22.tif, 262278 , 2018-04-19
Unet-master\images\train\label\23.tif, 262278 , 2018-04-19
Unet-master\images\train\label\24.tif, 262278 , 2018-04-19
Unet-master\images\train\label\25.tif, 262278 , 2018-04-19
Unet-master\images\train\label\26.tif, 262278 , 2018-04-19
Unet-master\images\train\label\27.tif, 262278 , 2018-04-19
Unet-master\images\train\label\28.tif, 262278 , 2018-04-19
Unet-master\images\train\label\29.tif, 262278 , 2018-04-19
Unet-master\images\train\label\3.tif, 262278 , 2018-04-19
Unet-master\images\train\label\4.tif, 262278 , 2018-04-19
Unet-master\images\train\label\5.tif, 262278 , 2018-04-19
Unet-master\images\train\label\6.tif, 262278 , 2018-04-19
Unet-master\images\train\label\7.tif, 262278 , 2018-04-19
Unet-master\images\train\label\8.tif, 262278 , 2018-04-19
Unet-master\images\train\label\9.tif, 262278 , 2018-04-19
Unet-master\test_predict.py, 1230 , 2018-04-19
Unet-master\unet.py, 9182 , 2018-04-19

下载说明:请别用迅雷下载,失败请重下,重下不扣分!

发表评论


0 个回复

  • NXP-mf
    NXP RC531 PN512 DS 官方英文版 Directly Matched Antenna Design(RC531 PN512 datasheet Directly Matched Antenna Design)
    2012-09-21 10:20:50下载
    积分:1
  • minimax
    用matlab程序求解最接近M的多项式函数(Solve the polynomial function closest to M using Matlab)
    2020-06-21 10:40:02下载
    积分:1
  • Android 滑出侧边栏特效 拉出抽屉效果
    Android 滑出侧边栏特效 拉出抽屉效果,就像抽屉抽出来合上去,打开手机界面后,侧边栏隐藏屏幕左侧,手放上去会有响应,然后向屏幕右侧滑,就打开侧边栏了,这里面可以是菜单或其它的相关内容,本例将向大家演示如何在Android的界面设计中实现这种效果。
    2022-03-26 16:46:12下载
    积分:1
  • matlab混沌加密
    利用matlab软件来实现混沌图像加密、解密的过程(Matlab implementation of chaotic image encryption process)
    2018-04-27 10:26:20下载
    积分:1
  • ssd_keras-master
    SSD图像识别,基于keras平台,识别速度的识别精度都还可以。(SSD image recognition, based on keras platform, the recognition accuracy of recognition speed is also acceptable.)
    2019-01-21 10:47:10下载
    积分:1
  • AD7192
    说明:  可较好实现AD7192功能,能够有效采集数据,(The function of AD7192 can be well realized.)
    2019-02-26 14:44:41下载
    积分:1
  • 用C++开发贪吃蛇的游戏,一款益智游戏。
    用C++开发贪吃蛇的游戏,一款益智游戏。 -With C++ Development of Snake game, a puzzle game.
    2022-02-12 02:30:08下载
    积分:1
  • 地闪计算
    说明:  计算底面闪电次数,根据结果结合surfer可生成平面图。(According to the results and surfer, the plan can be generated.)
    2021-03-23 10:59:16下载
    积分:1
  • 这个是Haffman的实现方法,也就是还可以的代码,希望采纳,^_^...
    这个是Haffman的实现方法,也就是还可以的代码,希望采纳,^_^-this is the method, which is also the code, adopted ^ _ ^
    2022-02-25 15:33:11下载
    积分:1
  • 四阶龙格库塔法解数值微分
    说明:  程序主要实现了四阶龙哥库塔,程序注释很详细(The fourth-order Longkouta is mainly realized, and the program annotations are very detailed.)
    2019-04-29 22:12:19下载
    积分:1
  • 696518资源总数
  • 104591会员总数
  • 57今日下载