2018-12-07 21:20:09 qq_15029743 阅读数 9354

摘自:https://blog.csdn.net/zhaomengszu/article/details/78347388

中国计算机学会推荐国际学术会议 

(计算机图形学与多媒体)

一、A类

序号

会议简称

会议全称

出版社

网址

1

ACM MM

ACM International Conference on Multimedia

ACM

http://www.acmmm12.org/

2

SIGGRAPH

ACM SIGGRAPH Annual Conference

ACM

http://www.siggraph.org/

3

IEEE VIS

IEEE Visualization Conference

IEEE

http://www.ieeevis.org/

二、B类

序号

会议简称

会议全称

出版社

网址

1

ICMR

ACM SIGMM International Conference on Multimedia Retrieval

ACM

http://impact.utc.edu/icmr2013/

2

i3D

ACM Symposium on Interactive 3D Graphics

ACM

http://www.csee.umbc.edu/csee/research/vangogh
/I3D2013/

3

SCA

ACM/Eurographics Symposium on Computer Animation

ACM

http://www.cs.ubc.ca/~van/sca/sca.html

4

DCC

Data Compression Conference

IEEE

http://www.cs.brandeis.edu/~dcc/

5

EG

Eurographics

Wiley/ Blackwell

http://www.eg.org/

6

EuroVis

Eurographics Conference on Visualization

ACM

http://www.eurovis2013.de/

7

SGP

Eurographics Symposium on Geometry Processing

Wiley/ Blackwell

http://www.ioc.ee/sgp12/

8

EGSR

Eurographics Symposium on Rendering

Wiley/ Blackwell

http://webdiis.unizar.es/EGSR2013/

9

ICME

IEEE International Conference on 
Multimedia &Expo

IEEE

http://www.icme2012.org/

10

PG

Pacific Graphics: The Pacific Conference on Computer Graphics and Applications

Wiley/ Blackwell

http://sweb.cityu.edu.hk/pg2012/

11

SPM

Symposium on Solid and Physical Modeling

SMA/Elsevier

http://www.siam.org/meetings/gdspm13/

三、C类

序号

会议简称

会议全称

出版社

网址

1

CASA

Computer Animation and Social Agents

Wiley

http://www.cs.bilkent.edu.tr/~casa2013/

2

CGI

Computer Graphics International

Springer

http://cgi2013.welfenlab.de/

3

ISMAR

International Symposium on Mixed and Augmented Reality

IEEE/ACM

http://ismar.vgtc.org/

4

PacificVis

IEEE Pacific Visualization Symposium

IEEE

http://rp-www.cs.usyd.edu.au/~visual/pvis2013/
welcome/index.php

5

ICASSP

IEEE International Conference on Acoustics, Speech and SP

IEEE

http://www.icassp2013.com/

6

ICIP

International Conference on Image Processing

IEEE

http://www.ieeeicip.org/

7

MMM

International Conference on Multimedia Modeling

Springer

http://mmm2013.org/

8

GMP

Geometric Modeling and Processing

Elsevier

http://math.ustc.edu.cn/Conference/GMP2012/

9

PCM

Pacific-Rim Conference on Multimedia

Springer

http://cemnet.ntu.edu.sg/pcm2012/

10

SMI

Shape Modeling International

IEEE

http://www.shapemodeling.org/

中国计算机学会推荐国际学术会议
(人工智能与模式识别)

一、A类

序号

会议简称

会议全称

出版社

网址

1

AAAI

AAAI Conference on Artificial Intelligence

AAAI

http://www.aaai.org

2

CVPR

IEEE Conference on Computer Vision and 
Pattern Recognition

IEEE

http://www.pamitc.org/cvpr13/

3

ICCV

International Conference on Computer
Vision

IEEE

http://www.iccv2013.org/

4

ICML

International Conference on Machine 
Learning

ACM

http://icml.cc/2013/

5

IJCAI

International Joint Conference on Artificial
Intelligence

Morgan Kaufmann

http://www.ijcai.org

二、B类

序号

会议简称

会议全称

出版社

网址

1

COLT

Annual Conference on Computational
Learning Theory

Springer

http://orfe.princeton.edu/conferences/colt2013/

2

NIPS

Annual Conference on Neural Information
Processing Systems

MIT Press

http://www.nips.cc

3

ACL

Annual Meeting of the Association for 
Computational Linguistics

ACL

http://acl2013.org/site/index.html

4

EMNLP

Conference on Empirical Methods in Natural
Language Processing

ACL

http://www.sigdat.org/

5

ECAI

European Conference on Artificial 
Intelligence

IOS Press

http://www.ecai2013.upit.ro/?i=2542

6

ECCV

European Conference on Computer Vision

Springer

http://eccv2012.unifi.it/

7

ICRA

IEEE International Conference on Robotics
and Automation

IEEE

http://www.icra2013.org/

8

ICAPS

International Conference on Automated
Planning and Scheduling

AAAI

http://www.icaps-conference.org/

9

ICCBR

International Conference on Case-Based
Reasoning

Springer

http://www.iccbr.org/

10

COLING

International Conference on Computational
Linguistics

ACM

 http://www.coling2012-iitb.org/

11

KR

International Conference on Principles of
Knowledge Representation and Reasoning

Morgan Kaufmann

http://www.kr.org/

12

UAI

International Conference on Uncertainty
in Artificial Intelligence

AUAI

http://auai.org/

13

AAMAS

International Joint Conference
on Autonomous Agents and Multi-agent
Systems

Springer

http://www.aamas-conference.org/

三、C类

序号

会议简称

会议全称

出版社

网址

1

ACCV

Asian Conference on Computer Vision

Springer

http://www.accv2012.org/

2

CoNLL

Conference on Natural Language Learning

CoNLL

http://www.clips.ua.ac.be/conll/

3

GECCO

Genetic and Evolutionary Computation
Conference

ACM

http://www.sigevo.org/gecco-2013/

4

ICTAI

IEEE International Conference on Tools with
Artificial Intelligence

IEEE

http://ictai12.unipi.gr/

5

ALT

International Conference on Algorithmic
Learning Theory

Springer

http://www-alg.ist.hokudai.ac.jp/~thomas/ALT13/

6

ICANN

International Conference on Artificial Neural
Networks

Springer

https://www.waset.org/conferences/2013/
amsterdam/icann/

7

FGR

International Conference on Automatic Face
and Gesture Recognition

IEEE

http://fg2013.cse.sc.edu/

8

ICDAR

International Conference on Document
Analysis and Recognition

IEEE

http://www.icdar2013.org/

9

ILP

International Conference on Inductive Logic
Programming

Springer

http://ilp13.cos.ufrj.br/

10

KSEM

International conference on Knowledge
Science,Engineering and Management

Springer

http://ksem.dlut.edu.cn/

11

ICONIP

International Conference on Neural 
Information Processing

Springer

http://iconip2013.org/

12

ICPR

International Conference on Pattern 
Recognition

IEEE

http://www.icpr2014.org/

13

ICB

International Joint Conference on Biometrics

IEEE

http://atvs.ii.uam.es/icb2013/

14

IJCNN

International Joint Conference on Neural
Networks

IEEE

http://www.ijcnn2013.org/

15

PRICAI

Pacific Rim International Conference on 
Artificial Intelligence

Springer

http://ktw.mimos.my/pricai2012/

16

NAACL

The Annual Conference of the North
American Chapter of the Association 
for Computational Linguistics

NAACL

http://naacl2013.naacl.org/

17

BMVC

British Machine Vision Conference

British Machine
Vision 
Association

http://bmvc2013.bristol.ac.uk/

2011-10-23 19:24:41 TJU355 阅读数 15643

  通信类权威会议,微笑
A类会议:本学科最顶尖级水平的国际会议;
B类会议:学术水平较高、组织工作成熟、按一定时间间隔系列性召开的国际会议。

A类会议(序号不表示优先顺序)
序号/英文名称/英文简称/中文名称/备注
1    IEEE International Conference on Acoustics, Speech and Signal Processing/ ICASAP/   IEEE声学、语音和信号处理国际会议    
2    IEEE International Conference on Image Processing/ ICIP/    IEEE图像处理国际会议    
3   International Conference on Pattern Recognition/    ICPR/   模式识别国际会议    
4   IEEE International Conference on Communications/    ICC/   IEEE通信国际会议    (这个和下面经常被老师挂在嘴边,对我们来说只是传说啦)
5    IEEEGlobal Telecommunications Conference/    Globecom/    IEEE全球电信会议    
6    IEEEInternational Conference on Intelligent TransportationSystem/    ITSC/   IEEE智能交通系统国际会议    
7   Annual IEEE Conference on Computer Communications/    IEEEINFOCOM/    IEEE计算机通信会议   
8    IEEERadar Conference/    IEEE雷达会议    


B类会议(序号不表示优先顺序)
序号/英文名称/英文简称/中文名称/备注
1   International Conference On Natural Language Processing/   ICON/   自然语言处理国际会议    
2   International Conference on Telecommunications/ ICT/    电信国际会议    
3   International Geoscience and Remote Sensing Symposium/   IGARSS/   地球科学与遥感国际研讨会    
4   Picture Coding Symposium/ PCS/   图像编码研讨会    
5   ACM Conference on Computer and Communications Security/ CS/   ACM计算机与通信安全会议 
6    IEEEMilitary Communications Conference/    MILCOM/   IEEE军事通信会议    
7   International Broadcasting Convention/    IBC/   国际广播会议    
8   IEEE Wireless Communications & Networking Conference/   WCNC/    IEEE无线通信和网络会议   
9    SPIEConference on Visual Communications and Image Processing/   VCIP/    SPIE视觉通信和图像处理会议    
10   International Symposium on Wireless Personal MultimediaCommunications/    WPMC/    无线个人多媒体通信国际研讨会   
11   IEEE International Conference on Third Generation Wireless and Beyond/3G andBeyond/IEEE第三代及以上无线通信国际会议  
12    ACMMobicom/    ACM/移动通信会议    
13   International Conference on Network Protocol/ ICNP/   网络协议国际会议    
14   IEEE Speech Coding Workshop    
15   International Conference on Speech and Language Processing/   ICSLP/   语音语言处理国际会议
16   International Symposium on Chinese Spoken LanguageProcessing/    ISCSLP/   中文口语语言处理国际会议
17   MOBI COM & MOBI HOC/    移动Ad hoc移动通信会议/    Ad hoc的顶级年会
18   Vehicular Technology Conference/ VTC/   国际传输技术会议/    与产业界结合比较紧密的会2次/年
19    ACMConference on Embedded Networked Sensor Systems Sensys/嵌入式网络传感系统/ WSN的顶级年会(Single Track的小会)
20   Global Navigation Satellite Systems/    ION/IEEEGNSS/   全球导航卫星系统会议/    IEEE和美国导航学会联合召开的年会
21   International conference on Radar/   ICR/  英美法中澳五国轮流召开
22   IEEE Conference on Computer Vision and Pattern Recognition/    CVPR/   计算机视觉与模式识别会议
23   IEEE International Conference on Multimedia & Expo/   ICME/   多媒体IEEE 国际会议及展览会/    每年召开
24   IEEE International conference on Computer Vision/   ICCV/   计算机视觉IEEE国际会议/    
25   International Conference on Document Analysis and Recognition/ICDAR/文档分析和识别国际会议/文字识别领域最重要的会议,每两年召开一次,07年是第九届


通信一些期刊的影响因子:

1 IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 1.328 
2
IEEE COMMUNICATIONS MAGAZINE 1.291 
3 IEEE NETWORK 1.288 
4 RADIO SCIENCE 1.059 
5
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION1.011 
6
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 0.812 
7 IEEE TRANSACTIONS ON COMMUNICATIONS 0.681 
8 TELECOMMUNICATIONS POLICY 0.586 
9 IEE PROCEEDINGS-OPTOELECTRONICS 0.545 
10 BT TECHNOLOGY JOURNAL 0.454 
11 IEEE TRANSACTIONS ON ELECTROMAGNETICCOMPATIBILITY 0.421 
12 IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONICSYSTEMS 0.381 
13 IEE PROCEEDINGS-MICROWAVES ANTENNAS ANDPROPAGATION 0.380 
14 IEEE TRANSACTIONS ON BROADCASTING 0.353 
15 IEICE TRANSACTIONS ON COMMUNICATIONS 0.350 
16 IEE PROCEEDINGS-RADAR SONAR AND NAVIGATION0.313 
17 SMPTE JOURNAL 0.265 
18 IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 0.233 
19 ELECTRONICS & COMMUNICATION ENGINEERINGJOURNAL 0.208 
20 ANNALES DES TELECOMMUNICATIONS-ANNALS OFTELECOMMUNICATIONS 0.105 
21 JOURNAL OF COMMUNICATIONS TECHNOLOGY ANDELECTRONICS 0.084



2019-05-16 16:37:37 tech_otaku0512 阅读数 378

寒武纪科技:

  1. 熟悉Tensflow/Mxnet/Caffe等深度学习平台架构;
  2. 熟悉opencv等常见cv库的使用;
  3. Linux编程开发经验;

SenTime商汤科技:

  1. 较强的算法实现能力,熟练掌握 C/C++ 编程,熟悉 Shell/Python/Matlab 编程;
  2. 如研究生发表过第一作者CCF A类会议或期刊等论文,或本科发表过第一作者CCF B类以上会议或期刊论文;
  3. 有较强的代码能力优先,获得过ACM或其他商业代码竞赛的荣誉,如ACM区预赛金牌、NOI银牌以上、百度之星决赛等;
  4. 比如ImageNet等学术数据集或者Kaggle等一些国内外商业比赛;
  5. 基本的算法设计和实现能力,熟悉Python/C++/CUDA编程,掌握PyTorch/TensorFlow/MXNet等框架;
  6. 在相关领域顶级期刊或会议发表过论文优先;
  7. 三维视觉或计算机图形学研究经历优先;

Megvil旷视:

  1. 完成过 MIT 6.824 或同等分布式系统课程;
  2. 开源分布式存储系统(如 Ceph, HDFS)开发经验;
  3. 熟练掌握 Go/C++, 有一定项目经验;
  4. 熟悉 Python 等至少一门脚本语言,使用过 Theano, Caffe, Torch, TensorFlow 等开源深度学习框架优先;
  5. 有深度模型训练,图像分类、物体检测与分割、视频分析、三维建模、计算机图形学等相关科研经历者(例如顶级会议第一作者)优先;
  6. 深度学习/机器学习;计算机视觉(包括分类,检测,分割,跟踪,SLAM和三维重建);
  7. 熟悉本研究领域的最新研究成果,公开数据集,和相关的开源系统;

深兰科技上海:

  1. 计算机基础知识扎实,熟练掌握Python、C/C++/C#、Java中的一种
  2. 有图像处理领域相关竞赛经验者优先;有OCR领域图像处理经验者优先, 有活体检测经验者优先;
  3. 本科及以上学历,计算机、自动化、通信等相关专业;
  4. 熟悉计算机视觉基本理论知识,熟练掌握OpenCV,并具备至少1年以上的相关工作经验;
  5. 熟练掌握计算机视觉和图像处理基本算法,并在以下某个或多个方向有深入研究者优先:如图像识别理解,人脸检测识别、目标检测和跟踪、图像质量评价,图像分割增强等;

Bilibili:

1、负责APP产品的视频图像处理模块的设计和研发;
2、研究创新产品体验。

工作要求:

  1. 至少5年以上相关工作经验,本科以上学历,计算机软件或相关专业;
  2. 有扎实的OC/JAVA/C++语言基础,理解面向对象设计基本原则,能熟练运用常用设计模式;
  3. 熟练掌握OpenGL,图像滤镜处理相关的技能;
  4. 熟悉流媒体相关处理技术,熟悉常见的图像处理和音视频。

酷我:

  1. 图像处理、计算机视觉专业方向,本科及以上学历;
  2. 熟练使用C/C++编程语言;
  3. 熟悉图像处理基本方法(边缘检测,区域提取,低通滤波,特征提取,交点检测,二值化等),具备相关领域研究和实现;
  4. 熟练使用OpenCV进行视觉应用开;
2018-10-21 17:47:55 weixin_41977512 阅读数 10349

参考论文:Residual Attention Network for Image Classification,发表与2017年CVPR会议上

一、前言
在分析这个网络前首先应该明确注意力机制的本质:一系列的注意力分配系数,也就是一系列权重参数,可以用来强调或选择目标处理对象的重要信息,并且抑制一些无关的细节信息。
论文中作者对所提出的残差注意力网络的定义是:A convolutional network that adopts mixed attention mechanism in “very deep” structure.也就是说这个网络首先是一个卷积神经网络,只是它的特点在于引入了混合注意力机制,并且网络结构非常地深。我将分别从这两个方面进行介绍。
二、图像处理中注意力机制的实现
1、引入注意力机制的意义
1)选择聚焦位置,产生更具分辨性的特征表示
网络由大量的注意力模块(Attention Module)组成,能产生注意力感知的(attention-aware)的特征,并且不同模块的特征随着网络的加深会产生适应性改变。
2)渐增的注意力模块将带来持续的性能提升
不同类型的attention将被大量捕捉到。
下图形象地说明了注意力机制的作用原理,也阐明了以上所说的两点。
在这里插入图片描述
左边部分展示了注意力掩模与特征图的作用机制。右边部分主要说明随着网络的加深所能关注到的特征级别也会越来越高。比如说当网络比较浅的时候,注意力只能捕捉到像颜色特征这样的低级别特征,图的中间就是对蓝色天空都分的一个抑制。而当网络比较深的时候,注意力就能捕捉一些高级别特征,如左边对热气球底部的一个强调。
2、注意力机制的实现
1)总体结构
(1)由多个注意力模块堆叠而成
(2)每个注意力模块被分成了两个分支:mask brunch 和 trunk branch
(3)注意力模块的输出为:Hi,c(x)=Mi,c(x)Ti,c(x)H_i,c(x)=M_i,c(x)*T_i,c(x)
Mi,cM_i,c是mask分支输出的注意力权重,Ti,cT_i,c是trunk分支经过一系列操作所提取出的特征图表示,输出即为二者的点积。
在这里插入图片描述
在这里插入图片描述
2)分支剖析
(1)trunk分支
与传统的卷积网络特征处理相似,通过多次卷积操作提取特征。
(2)mask分支
是注意力模块的核心部件,主要由一个buttom-up top-down的结构,这种结构也是一种encoder-decoder模型,形状与沙漏网络(hourglass network)相似。
沙漏网络
buttom-up部分:执行下采样(down sample),多次进行最大池化操作扩大接受域,直到达到最低分辨率。作用效果是:产生低分辨率、强语义信息的特征图,从而收集整个图片的全局信息。
top-down部分:执行上采样(up sample)线性插值,直到特征图尺寸与输入时相等。作用效果是:扩展Bottom-up所产生的特征图,使其尺寸与输入Bottom-up前的特征图大小相同,从而对输入特征图的每个像素进行推理选择。
所以,综上mask分支的作用总结如下:
前向推导中主要起特征选择的作用,可将mask分支的输出看作是trunk分支神经元的控制门,过滤不重要的信息,强调重要信息。
后向传播中起梯度更新过滤的作用。由于mask分支仅进行下采样和上采样操作,所以在反向传播中没有参数更新,那么它对trunk分支的选择性将不会改变,即使有噪音标签更新了trunk分支中的参数,mask分支也会将其剔除掉,这使得网络对于标签噪音具有很好的健壮性。
3)注意力的分类
在mask 输出之前,通过改变激活函数中的标准化方式,对mask 中的Attention添加不同的约束,可以产生三种类型的attention。
在这里插入图片描述
实验表明不添加任何约束的mixed attention的错误率最低!
3、网络深度的扩展
在对网络深度进行扩展时,主要存在的问题是,简单的注意力模块堆叠会造成明显的性能下降,原因如下:
1)mask的取值范围为[0,1],在深层网络中重复地进行点积,会消减特征的值。
2)mask潜在地打破了trunk分支的一些特性,比如说残差单元的恒等映射(identical mapping)
解决方案:作者类比残差学习提出了注意力残差学习,仿其提出假设:如果mask单元能被构造成恒等映射,那么它的性能将不会比没有注意力机制的网络差。
在这里插入图片描述

2019-02-15 12:56:46 weixin_43765314 阅读数 2093

VGG net

VGG net是 Karen simonyan 等人在2015年的CLR会议中公开的神经网络模型。这个模型在2014年的Imagenet比赛中获得了定位第一名和分类第二名的好成绩,它的主要贡献在于利用3×3小卷积核的网络结构对逐渐加深的网络进行评估,结果表明加深网络深度到16至19层可极大提高模型精度。

架构:

训练输入:固定尺寸224×224的RGB图像

预处理:每个像素值减去训练集上的RGB均值

卷积核:一系列3×3卷积核堆叠,步长为1,采用padding保持卷积后图像空间分辨率不变。

空间池化:紧随卷积堆的最大池化,为2×2滑动窗口,步长为2

全连接层:特征提取完成后,接三个全连接层,前两个为4096通道,第三个为1000通道,最后一个是soft-max层,输出概率

下表每列代表不同的网络,只有深度不同(层数计算不包括池化层)。卷积的通道数量很小,第一层仅64通道,每经过一次最大池化,通道数翻倍,直到数量达到512通道。


函数用法

np.load() 将数组以二进制形式读出磁盘,扩展名为.npy
data_dict=np.load(vgg16.npy,encoding='latin').item() 读取vgg16.npy文件,遍历其内键值对,导出模型参数赋给data_dict.
tf.reshape(tensor,[n行,m列]) 可以把张量变成需要的维度
tf.reshape(tensor,[-1,m列]) 表示根据其他维度自动调整
np.argsort() 把列表从小到大排序,返回的是索引值
os.getced() 返回当前工作目录

tf.shape()可以打印出数据(张量、列表数组)的维度:

import tensorflow as tf
import numpy as np
x=tf.constant([[1,2,3],[4,5,6]])#tensor
y=[[1,2,3],[4,5,6]]             #list
z=np.arange(24).reshape([2,3,4])#array

sess=tf.Session()

sess.run(tf.shape(x))
array([2, 3], dtype=int32)#二维

sess.run(tf.shape(y))
array([2, 3], dtype=int32)#二维

sess.run(tf.shape(z))
array([2, 3, 4], dtype=int32)#三维

tf.split(切谁,怎么切,在哪个维度切) :

A=[[1,2,3],[4,5,6]]
>>> y=tf.split(A,3,1)
>>> c=sess.run(y)
>>> for i in c:
...     print(i)
... 
[[1]
 [4]]
[[2]
 [5]]
[[3]
 [6]]

上面的操作把A在第一个维度(列)上分为3份。


复现VGG-16

app.py:应用程序,实现图像识别

vgg16.py:读模型参数,搭建模型

utils.py:读入图片,概率显示

Nclass.py:含lables字典,根据键找出值,也就是类别

vgg16.npy:网络参数,下载地址: 密码:umce

app.py:应用程序,实现图像识别:

#coding:utf-8
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
import vgg16
import utils
from Nclasses import labels

img_path = input('Input the path and image name:')
img_ready = utils.load_image(img_path) #调用load_image()函数,对待测试的图像做一些预处理操作
print('img_ready shape',tf.Session().run(tf.shape(img_ready)))#打印出img_ready的维度

fig=plt.figure("Top-5 预测结果") #定义一个画图窗口,把识别结果显示在柱状图中

with tf.Session() as sess:
    images = tf.placeholder(tf.float32, [1, 224, 224, 3])#输入图片的尺寸
    vgg = vgg16.Vgg16() #实例化vgg,读出vgg16.npy中的模型参数
    vgg.forward(images) #传入图片,前向传播
    probability = sess.run(vgg.prob, feed_dict={images:img_ready})#将一个batch的数据喂入网络,得到网络的预测输出

    #np.argsort()函数返回预测值由小到大的索引值(标签字典中的键),并取出预测概率最大的五个索引值
    top5 = np.argsort(probability[0])[-1:-6:-1]
    print ("top5:",top5)
    #定义两个list--对应的概率值和实际标签
    values = []#存probability中元素的值,5个物种出现概率
    bar_label = []#存标签字典中对应的值,即5个物种的名称
    #枚举上面取出的五个索引值
    for n, i in enumerate(top5): 
        print ("n:",n)
        print ("i:",i)
        values.append(probability[0][i])#将索引值对应的预测概率值取出并放入values
        bar_label.append(labels[i]) #根据索引值取出对应的实际标签并放入bar_lable
        print (i, ":", labels[i], "----", utils.percent(probability[0][i]))#打印属于某个类别的概率
        
    ax = fig.add_subplot(111) #把画布划为一行一列,并把下图放入其中
    #bar函数绘制柱状图,参数range(len(values))是柱子下标,values表示柱高的列表(也就是五个概率值
    # tick_lable是每个柱子上显示的标签(实际对应的标签),width是柱子的宽度,fc是柱子的颜色)
    ax.bar(range(len(values)), values, tick_label=bar_label, width=0.5, fc='g')
    ax.set_ylabel(u'probabilityit') #设置横轴标签
    ax.set_title(u'Top-5') #添加标题
    for a,b in zip(range(len(values)), values):
        #在每个柱子的顶端添加对应的预测概率值,a,b表示坐标,b+0.00005表示要把文本信息放置在高于每个柱子顶端0.00005的位置
        #center是表示文本位于柱子顶端水平方向上的中间位置,bottom是将文本水平放置在柱子顶端垂直方向上的底端位置,fontsize是字号
        ax.text(a, b+0.0005, utils.percent(b), ha='center', va = 'bottom', fontsize=7)   
    plt.show() 


    

vgg16.py:读模型参数,搭建模型:

import inspect
import os
import numpy as np
import tensorflow as tf
import time
import matplotlib.pyplot as plt

VGG_MEAN = [103.939, 116.779, 123.68] #样本RGB的平均值

class Vgg16():
    def __init__(self, vgg16_path=None):#导入模型参数
        if vgg16_path is None:
            vgg16_path = os.path.join(os.getcwd(), "vgg16.npy") #os.getcwd()用于返回当前工作目录
            print(vgg16_path)
            self.data_dict = np.load(vgg16_path, encoding='latin1').item() #遍历其内键值对,导入模型参数
                                                                           #键是每一层网络名称,值是这一层网络的所有参数,

        for x in self.data_dict:#遍历data_dict中的每个键
            print(x)

    def forward(self, images):
        
        print("build model started")
        start_time = time.time() #获取前向传播的开始时间
        rgb_scaled = images * 255.0 #逐像素乘以255.0(根据原论文所述的初始化步骤)

        #从RGB转换色彩通道到BGR,也可使用cv中的GRBtoBGR
        red, green, blue = tf.split(rgb_scaled,3,3) #在第三个维度切分为三份,分别赋给红、绿、蓝
        bgr = tf.concat([     
            blue - VGG_MEAN[0],
            green - VGG_MEAN[1],
            red - VGG_MEAN[2]],3)
        #逐样本减去每个通道的像素平均值,这种操作可以移除图像的平均亮度值,该方法用在灰度图像上


        #接下来构建VGG的16层网络(包含5段卷积,3层全连接),并逐层根据命名空间读取网络参数
        #第一段卷积,含有两个卷积层,后面接最大池化层,用来缩小图片尺寸
        self.conv1_1 = self.conv_layer(bgr, "conv1_1")
        #传入命名空间的name,来获得该层的卷积核和偏置,并作卷积运算,最后返回经过激活函数后的值
        self.conv1_2 = self.conv_layer(self.conv1_1, "conv1_2")
        #根据传入的pooling名字对该层作相应的池化操作
        self.pool1 = self.max_pool_2x2(self.conv1_2, "pool1")

        #下面的前向传播过程与第一段同理
        #第二段卷积,同样包含两个卷积层,一个最大池化层
        self.conv2_1 = self.conv_layer(self.pool1, "conv2_1")
        self.conv2_2 = self.conv_layer(self.conv2_1, "conv2_2")
        self.pool2 = self.max_pool_2x2(self.conv2_2, "pool2")

        #第三段卷积,包含三个卷积层,一个最大池化层
        self.conv3_1 = self.conv_layer(self.pool2, "conv3_1")
        self.conv3_2 = self.conv_layer(self.conv3_1, "conv3_2")
        self.conv3_3 = self.conv_layer(self.conv3_2, "conv3_3")
        self.pool3 = self.max_pool_2x2(self.conv3_3, "pool3")

        #第四段卷积,包含三个卷积层,一个最大池化层
        self.conv4_1 = self.conv_layer(self.pool3, "conv4_1")
        self.conv4_2 = self.conv_layer(self.conv4_1, "conv4_2")
        self.conv4_3 = self.conv_layer(self.conv4_2, "conv4_3")
        self.pool4 = self.max_pool_2x2(self.conv4_3, "pool4")

        # 第五段卷积,包含三个卷积层,一个最大池化层
        self.conv5_1 = self.conv_layer(self.pool4, "conv5_1")
        self.conv5_2 = self.conv_layer(self.conv5_1, "conv5_2")
        self.conv5_3 = self.conv_layer(self.conv5_2, "conv5_3")
        self.pool5 = self.max_pool_2x2(self.conv5_3, "pool5")

        #第六段全连接层
        self.fc6 = self.fc_layer(self.pool5, "fc6") 
        self.relu6 = tf.nn.relu(self.fc6)

        # 第七段全连接层
        self.fc7 = self.fc_layer(self.relu6, "fc7")
        self.relu7 = tf.nn.relu(self.fc7)

        # 第八段全连接层
        self.fc8 = self.fc_layer(self.relu7, "fc8")
        #经过最后一层的全连接后,再做softmax分类,得到属于各类别的概率
        self.prob = tf.nn.softmax(self.fc8, name="prob")
        
        end_time = time.time() #得到前向传播的结束时间
        print(("time consuming: %f" % (end_time-start_time)))

        self.data_dict = None #清空本次读取到的模型参数字典

    #定义卷积运算
    def conv_layer(self, x, name):
        with tf.variable_scope(name):#根据命名空间找到对应卷积层的网络参数
            w = self.get_conv_filter(name) #读到该层的卷积核
            conv = tf.nn.conv2d(x, w, [1, 1, 1, 1], padding='SAME')#卷积计算
            conv_biases = self.get_bias(name) #读到偏置项
            result = tf.nn.relu(tf.nn.bias_add(conv, conv_biases))#加上偏置,并做激活计算
            return result

    #定义获取卷积核的函数
    def get_conv_filter(self, name):
        #根据命名空间name从字典中取到对应的卷积核
        return tf.constant(self.data_dict[name][0], name="filter") 

    #定义偏置项获取函数
    def get_bias(self, name):
        # 根据命名空间name从字典中取到对应的卷积核
        return tf.constant(self.data_dict[name][1], name="biases")

    #定义最大池化操作
    def max_pool_2x2(self, x, name):
        return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', name=name)

    #定义全连接层的前向传播计算
    def fc_layer(self, x, name):
        with tf.variable_scope(name):#根据命名空间name做全连接层的计算
            shape = x.get_shape().as_list() #获取该层的维度信息列表
            dim = 1
            for i in shape[1:]:
                dim *= i #将每层的维度相乘
            x = tf.reshape(x, [-1, dim])#改变特征图的形状,也就是将得到的多维特征做拉伸操作,只在进入第六层全连接做该操作
            w = self.get_fc_weight(name) #读到权重值
            b = self.get_bias(name) #读到偏置项值
                
            result = tf.nn.bias_add(tf.matmul(x, w), b)#对该层输入做加权就和,再加上偏置
            return result
    #定义获取权重的参数
    def get_fc_weight(self, name):  #根据命名空间name从参数字典中取到对应的权重
        return tf.constant(self.data_dict[name][0], name="weights")

utils.py:读入图片,概率显示:

#coding:utf-8
from skimage import io, transform
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from pylab import mpl

mpl.rcParams['font.sans-serif']=['SimHei'] # 正常显示中文标签
mpl.rcParams['axes.unicode_minus']=False # 正常显示正负号

def load_image(path):#对图片预处理,并显示待识别图片的每一次处理效果
    fig = plt.figure("Centre and Resize")#新建一个图
    img = io.imread(path) #读入
    img = img / 255.0 #将像素归一化0-1之间
    
    ax0 = fig.add_subplot(131)  #建立一行三列的子图,描述第一张子图
    ax0.set_xlabel(u'Original Picture') #添加子图标签
    ax0.imshow(img) 
    
    short_edge = min(img.shape[:2]) #找到这张图的最短边
    y = (img.shape[0] - short_edge) // 2  
    x = (img.shape[1] - short_edge) // 2 #把图像的w和h分别减去最短边并求平均
    crop_img = img[y:y+short_edge, x:x+short_edge] #取出切分后的中心图
    
    ax1 = fig.add_subplot(132) #把下面的图像放入一行三列图的第二个位置
    ax1.set_xlabel(u"Centre Picture") 
    ax1.imshow(crop_img)
    
    re_img = transform.resize(crop_img, (224, 224)) #固定分辨率
    
    ax2 = fig.add_subplot(133) #放到第三个位置
    ax2.set_xlabel(u"Resize Picture") 
    ax2.imshow(re_img)
	
    img_ready = re_img.reshape((1, 224, 224, 3))

    return img_ready

def percent(value):#把一个数字表示为百分比的形式
    return '%.2f%%' % (value * 100)

Nclass.py:含lables字典,根据键找出值,也就是类别:

#!/usr/bin/python
#coding:utf-8
# 每个图像的真实标签,以及对应的索引值
labels = {
 0: 'tench\n Tinca tinca',
 1: 'goldfish\n Carassius auratus',
 2: 'great white shark\n white shark\n man-eater\n man-eating shark\n Carcharodon carcharias',
 3: 'tiger shark\n Galeocerdo cuvieri',
 4: 'hammerhead\n hammerhead shark',
 5: 'electric ray\n crampfish\n numbfish\n torpedo',
 6: 'stingray',
 7: 'cock',
 8: 'hen',
 9: 'ostrich\n Struthio camelus',
 10: 'brambling\n Fringilla montifringilla',
 11: 'goldfinch\n Carduelis carduelis',
 12: 'house finch\n linnet\n Carpodacus mexicanus',
 13: 'junco\n snowbird',
 14: 'indigo bunting\n indigo finch\n indigo bird\n Passerina cyanea',
 15: 'robin\n American robin\n Turdus migratorius',
 16: 'bulbul',
 17: 'jay',
 18: 'magpie',
 19: 'chickadee',
 20: 'water ouzel\n dipper',
 21: 'kite',
 22: 'bald eagle\n American eagle\n Haliaeetus leucocephalus',
 23: 'vulture',
 24: 'great grey owl\n great gray owl\n Strix nebulosa',
 25: 'European fire salamander\n Salamandra salamandra',
 26: 'common newt\n Triturus vulgaris',
 27: 'eft',
 28: 'spotted salamander\n Ambystoma maculatum',
 29: 'axolotl\n mud puppy\n Ambystoma mexicanum',
 30: 'bullfrog\n Rana catesbeiana',
 31: 'tree frog\n tree-frog',
 32: 'tailed frog\n bell toad\n ribbed toad\n tailed toad\n Ascaphus trui',
 33: 'loggerhead\n loggerhead turtle\n Caretta caretta',
 34: 'leatherback turtle\n leatherback\n leathery turtle\n Dermochelys coriacea',
 35: 'mud turtle',
 36: 'terrapin',
 37: 'box turtle\n box tortoise',
 38: 'banded gecko',
 39: 'common iguana\n iguana\n Iguana iguana',
 40: 'American chameleon\n anole\n Anolis carolinensis',
 41: 'whiptail\n whiptail lizard',
 42: 'agama',
 43: 'frilled lizard\n Chlamydosaurus kingi',
 44: 'alligator lizard',
 45: 'Gila monster\n Heloderma suspectum',
 46: 'green lizard\n Lacerta viridis',
 47: 'African chameleon\n Chamaeleo chamaeleon',
 48: 'Komodo dragon\n Komodo lizard\n dragon lizard\n giant lizard\n Varanus komodoensis',
 49: 'African crocodile\n Nile crocodile\n Crocodylus niloticus',
 50: 'American alligator\n Alligator mississipiensis',
 51: 'triceratops',
 52: 'thunder snake\n worm snake\n Carphophis amoenus',
 53: 'ringneck snake\n ring-necked snake\n ring snake',
 54: 'hognose snake\n puff adder\n sand viper',
 55: 'green snake\n grass snake',
 56: 'king snake\n kingsnake',
 57: 'garter snake\n grass snake',
 58: 'water snake',
 59: 'vine snake',
 60: 'night snake\n Hypsiglena torquata',
 61: 'boa constrictor\n Constrictor constrictor',
 62: 'rock python\n rock snake\n Python sebae',
 63: 'Indian cobra\n Naja naja',
 64: 'green mamba',
 65: 'sea snake',
 66: 'horned viper\n cerastes\n sand viper\n horned asp\n Cerastes cornutus',
 67: 'diamondback\n diamondback rattlesnake\n Crotalus adamanteus',
 68: 'sidewinder\n horned rattlesnake\n Crotalus cerastes',
 69: 'trilobite',
 70: 'harvestman\n daddy longlegs\n Phalangium opilio',
 71: 'scorpion',
 72: 'black and gold garden spider\n Argiope aurantia',
 73: 'barn spider\n Araneus cavaticus',
 74: 'garden spider\n Aranea diademata',
 75: 'black widow\n Latrodectus mactans',
 76: 'tarantula',
 77: 'wolf spider\n hunting spider',
 78: 'tick',
 79: 'centipede',
 80: 'black grouse',
 81: 'ptarmigan',
 82: 'ruffed grouse\n partridge\n Bonasa umbellus',
 83: 'prairie chicken\n prairie grouse\n prairie fowl',
 84: 'peacock',
 85: 'quail',
 86: 'partridge',
 87: 'African grey\n African gray\n Psittacus erithacus',
 88: 'macaw',
 89: 'sulphur-crested cockatoo\n Kakatoe galerita\n Cacatua galerita',
 90: 'lorikeet',
 91: 'coucal',
 92: 'bee eater',
 93: 'hornbill',
 94: 'hummingbird',
 95: 'jacamar',
 96: 'toucan',
 97: 'drake',
 98: 'red-breasted merganser\n Mergus serrator',
 99: 'goose',
 100: 'black swan\n Cygnus atratus',
 101: 'tusker',
 102: 'echidna\n spiny anteater\n anteater',
 103: 'platypus\n duckbill\n duckbilled platypus\n duck-billed platypus\n Ornithorhynchus anatinus',
 104: 'wallaby\n brush kangaroo',
 105: 'koala\n koala bear\n kangaroo bear\n native bear\n Phascolarctos cinereus',
 106: 'wombat',
 107: 'jellyfish',
 108: 'sea anemone\n anemone',
 109: 'brain coral',
 110: 'flatworm\n platyhelminth',
 111: 'nematode\n nematode worm\n roundworm',
 112: 'conch',
 113: 'snail',
 114: 'slug',
 115: 'sea slug\n nudibranch',
 116: 'chiton\n coat-of-mail shell\n sea cradle\n polyplacophore',
 117: 'chambered nautilus\n pearly nautilus\n nautilus',
 118: 'Dungeness crab\n Cancer magister',
 119: 'rock crab\n Cancer irroratus',
 120: 'fiddler crab',
 121: 'king crab\n Alaska crab\n Alaskan king crab\n Alaska king crab\n Paralithodes camtschatica',
 122: 'American lobster\n Northern lobster\n Maine lobster\n Homarus americanus',
 123: 'spiny lobster\n langouste\n rock lobster\n crawfish\n crayfish\n sea crawfish',
 124: 'crayfish\n crawfish\n crawdad\n crawdaddy',
 125: 'hermit crab',
 126: 'isopod',
 127: 'white stork\n Ciconia ciconia',
 128: 'black stork\n Ciconia nigra',
 129: 'spoonbill',
 130: 'flamingo',
 131: 'little blue heron\n Egretta caerulea',
 132: 'American egret\n great white heron\n Egretta albus',
 133: 'bittern',
 134: 'crane',
 135: 'limpkin\n Aramus pictus',
 136: 'European gallinule\n Porphyrio porphyrio',
 137: 'American coot\n marsh hen\n mud hen\n water hen\n Fulica americana',
 138: 'bustard',
 139: 'ruddy turnstone\n Arenaria interpres',
 140: 'red-backed sandpiper\n dunlin\n Erolia alpina',
 141: 'redshank\n Tringa totanus',
 142: 'dowitcher',
 143: 'oystercatcher\n oyster catcher',
 144: 'pelican',
 145: 'king penguin\n Aptenodytes patagonica',
 146: 'albatross\n mollymawk',
 147: 'grey whale\n gray whale\n devilfish\n Eschrichtius gibbosus\n Eschrichtius robustus',
 148: 'killer whale\n killer\n orca\n grampus\n sea wolf\n Orcinus orca',
 149: 'dugong\n Dugong dugon',
 150: 'sea lion',
 151: 'Chihuahua',
 152: 'Japanese spaniel',
 153: 'Maltese dog\n Maltese terrier\n Maltese',
 154: 'Pekinese\n Pekingese\n Peke',
 155: 'Shih-Tzu',
 156: 'Blenheim spaniel',
 157: 'papillon',
 158: 'toy terrier',
 159: 'Rhodesian ridgeback',
 160: 'Afghan hound\n Afghan',
 161: 'basset\n basset hound',
 162: 'beagle',
 163: 'bloodhound\n sleuthhound',
 164: 'bluetick',
 165: 'black-and-tan coonhound',
 166: 'Walker hound\n Walker foxhound',
 167: 'English foxhound',
 168: 'redbone',
 169: 'borzoi\n Russian wolfhound',
 170: 'Irish wolfhound',
 171: 'Italian greyhound',
 172: 'whippet',
 173: 'Ibizan hound\n Ibizan Podenco',
 174: 'Norwegian elkhound\n elkhound',
 175: 'otterhound\n otter hound',
 176: 'Saluki\n gazelle hound',
 177: 'Scottish deerhound\n deerhound',
 178: 'Weimaraner',
 179: 'Staffordshire bullterrier\n Staffordshire bull terrier',
 180: 'American Staffordshire terrier\n Staffordshire terrier\n American pit bull terrier\n pit bull terrier',
 181: 'Bedlington terrier',
 182: 'Border terrier',
 183: 'Kerry blue terrier',
 184: 'Irish terrier',
 185: 'Norfolk terrier',
 186: 'Norwich terrier',
 187: 'Yorkshire terrier',
 188: 'wire-haired fox terrier',
 189: 'Lakeland terrier',
 190: 'Sealyham terrier\n Sealyham',
 191: 'Airedale\n Airedale terrier',
 192: 'cairn\n cairn terrier',
 193: 'Australian terrier',
 194: 'Dandie Dinmont\n Dandie Dinmont terrier',
 195: 'Boston bull\n Boston terrier',
 196: 'miniature schnauzer',
 197: 'giant schnauzer',
 198: 'standard schnauzer',
 199: 'Scotch terrier\n Scottish terrier\n Scottie',
 200: 'Tibetan terrier\n chrysanthemum dog',
 201: 'silky terrier\n Sydney silky',
 202: 'soft-coated wheaten terrier',
 203: 'West Highland white terrier',
 204: 'Lhasa\n Lhasa apso',
 205: 'flat-coated retriever',
 206: 'curly-coated retriever',
 207: 'golden retriever',
 208: 'Labrador retriever',
 209: 'Chesapeake Bay retriever',
 210: 'German short-haired pointer',
 211: 'vizsla\n Hungarian pointer',
 212: 'English setter',
 213: 'Irish setter\n red setter',
 214: 'Gordon setter',
 215: 'Brittany spaniel',
 216: 'clumber\n clumber spaniel',
 217: 'English springer\n English springer spaniel',
 218: 'Welsh springer spaniel',
 219: 'cocker spaniel\n English cocker spaniel\n cocker',
 220: 'Sussex spaniel',
 221: 'Irish water spaniel',
 222: 'kuvasz',
 223: 'schipperke',
 224: 'groenendael',
 225: 'malinois',
 226: 'briard',
 227: 'kelpie',
 228: 'komondor',
 229: 'Old English sheepdog\n bobtail',
 230: 'Shetland sheepdog\n Shetland sheep dog\n Shetland',
 231: 'collie',
 232: 'Border collie',
 233: 'Bouvier des Flandres\n Bouviers des Flandres',
 234: 'Rottweiler',
 235: 'German shepherd\n German shepherd dog\n German police dog\n alsatian',
 236: 'Doberman\n Doberman pinscher',
 237: 'miniature pinscher',
 238: 'Greater Swiss Mountain dog',
 239: 'Bernese mountain dog',
 240: 'Appenzeller',
 241: 'EntleBucher',
 242: 'boxer',
 243: 'bull mastiff',
 244: 'Tibetan mastiff',
 245: 'French bulldog',
 246: 'Great Dane',
 247: 'Saint Bernard\n St Bernard',
 248: 'Eskimo dog\n husky',
 249: 'malamute\n malemute\n Alaskan malamute',
 250: 'Siberian husky',
 251: 'dalmatian\n coach dog\n carriage dog',
 252: 'affenpinscher\n monkey pinscher\n monkey dog',
 253: 'basenji',
 254: 'pug\n pug-dog',
 255: 'Leonberg',
 256: 'Newfoundland\n Newfoundland dog',
 257: 'Great Pyrenees',
 258: 'Samoyed\n Samoyede',
 259: 'Pomeranian',
 260: 'chow\n chow chow',
 261: 'keeshond',
 262: 'Brabancon griffon',
 263: 'Pembroke\n Pembroke Welsh corgi',
 264: 'Cardigan\n Cardigan Welsh corgi',
 265: 'toy poodle',
 266: 'miniature poodle',
 267: 'standard poodle',
 268: 'Mexican hairless',
 269: 'timber wolf\n grey wolf\n gray wolf\n Canis lupus',
 270: 'white wolf\n Arctic wolf\n Canis lupus tundrarum',
 271: 'red wolf\n maned wolf\n Canis rufus\n Canis niger',
 272: 'coyote\n prairie wolf\n brush wolf\n Canis latrans',
 273: 'dingo\n warrigal\n warragal\n Canis dingo',
 274: 'dhole\n Cuon alpinus',
 275: 'African hunting dog\n hyena dog\n Cape hunting dog\n Lycaon pictus',
 276: 'hyena\n hyaena',
 277: 'red fox\n Vulpes vulpes',
 278: 'kit fox\n Vulpes macrotis',
 279: 'Arctic fox\n white fox\n Alopex lagopus',
 280: 'grey fox\n gray fox\n Urocyon cinereoargenteus',
 281: 'tabby\n tabby cat',
 282: 'tiger cat',
 283: 'Persian cat',
 284: 'Siamese cat\n Siamese',
 285: 'Egyptian cat',
 286: 'cougar\n puma\n catamount\n mountain lion\n painter\n panther\n Felis concolor',
 287: 'lynx\n catamount',
 288: 'leopard\n Panthera pardus',
 289: 'snow leopard\n ounce\n Panthera uncia',
 290: 'jaguar\n panther\n Panthera onca\n Felis onca',
 291: 'lion\n king of beasts\n Panthera leo',
 292: 'tiger\n Panthera tigris',
 293: 'cheetah\n chetah\n Acinonyx jubatus',
 294: 'brown bear\n bruin\n Ursus arctos',
 295: 'American black bear\n black bear\n Ursus americanus\n Euarctos americanus',
 296: 'ice bear\n polar bear\n Ursus Maritimus\n Thalarctos maritimus',
 297: 'sloth bear\n Melursus ursinus\n Ursus ursinus',
 298: 'mongoose',
 299: 'meerkat\n mierkat',
 300: 'tiger beetle',
 301: 'ladybug\n ladybeetle\n lady beetle\n ladybird\n ladybird beetle',
 302: 'ground beetle\n carabid beetle',
 303: 'long-horned beetle\n longicorn\n longicorn beetle',
 304: 'leaf beetle\n chrysomelid',
 305: 'dung beetle',
 306: 'rhinoceros beetle',
 307: 'weevil',
 308: 'fly',
 309: 'bee',
 310: 'ant\n emmet\n pismire',
 311: 'grasshopper\n hopper',
 312: 'cricket',
 313: 'walking stick\n walkingstick\n stick insect',
 314: 'cockroach\n roach',
 315: 'mantis\n mantid',
 316: 'cicada\n cicala',
 317: 'leafhopper',
 318: 'lacewing\n lacewing fly',
 319: "dragonfly\n darning needle\n devil's darning needle\n sewing needle\n snake feeder\n snake doctor\n mosquito hawk\n skeeter hawk",
 320: 'damselfly',
 321: 'admiral',
 322: 'ringlet\n ringlet butterfly',
 323: 'monarch\n monarch butterfly\n milkweed butterfly\n Danaus plexippus',
 324: 'cabbage butterfly',
 325: 'sulphur butterfly\n sulfur butterfly',
 326: 'lycaenid\n lycaenid butterfly',
 327: 'starfish\n sea star',
 328: 'sea urchin',
 329: 'sea cucumber\n holothurian',
 330: 'wood rabbit\n cottontail\n cottontail rabbit',
 331: 'hare',
 332: 'Angora\n Angora rabbit',
 333: 'hamster',
 334: 'porcupine\n hedgehog',
 335: 'fox squirrel\n eastern fox squirrel\n Sciurus niger',
 336: 'marmot',
 337: 'beaver',
 338: 'guinea pig\n Cavia cobaya',
 339: 'sorrel',
 340: 'zebra',
 341: 'hog\n pig\n grunter\n squealer\n Sus scrofa',
 342: 'wild boar\n boar\n Sus scrofa',
 343: 'warthog',
 344: 'hippopotamus\n hippo\n river horse\n Hippopotamus amphibius',
 345: 'ox',
 346: 'water buffalo\n water ox\n Asiatic buffalo\n Bubalus bubalis',
 347: 'bison',
 348: 'ram\n tup',
 349: 'bighorn\n bighorn sheep\n cimarron\n Rocky Mountain bighorn\n Rocky Mountain sheep\n Ovis canadensis',
 350: 'ibex\n Capra ibex',
 351: 'hartebeest',
 352: 'impala\n Aepyceros melampus',
 353: 'gazelle',
 354: 'Arabian camel\n dromedary\n Camelus dromedarius',
 355: 'llama',
 356: 'weasel',
 357: 'mink',
 358: 'polecat\n fitch\n foulmart\n foumart\n Mustela putorius',
 359: 'black-footed ferret\n ferret\n Mustela nigripes',
 360: 'otter',
 361: 'skunk\n polecat\n wood pussy',
 362: 'badger',
 363: 'armadillo',
 364: 'three-toed sloth\n ai\n Bradypus tridactylus',
 365: 'orangutan\n orang\n orangutang\n Pongo pygmaeus',
 366: 'gorilla\n Gorilla gorilla',
 367: 'chimpanzee\n chimp\n Pan troglodytes',
 368: 'gibbon\n Hylobates lar',
 369: 'siamang\n Hylobates syndactylus\n Symphalangus syndactylus',
 370: 'guenon\n guenon monkey',
 371: 'patas\n hussar monkey\n Erythrocebus patas',
 372: 'baboon',
 373: 'macaque',
 374: 'langur',
 375: 'colobus\n colobus monkey',
 376: 'proboscis monkey\n Nasalis larvatus',
 377: 'marmoset',
 378: 'capuchin\n ringtail\n Cebus capucinus',
 379: 'howler monkey\n howler',
 380: 'titi\n titi monkey',
 381: 'spider monkey\n Ateles geoffroyi',
 382: 'squirrel monkey\n Saimiri sciureus',
 383: 'Madagascar cat\n ring-tailed lemur\n Lemur catta',
 384: 'indri\n indris\n Indri indri\n Indri brevicaudatus',
 385: 'Indian elephant\n Elephas maximus',
 386: 'African elephant\n Loxodonta africana',
 387: 'lesser panda\n red panda\n panda\n bear cat\n cat bear\n Ailurus fulgens',
 388: 'giant panda\n panda\n panda bear\n coon bear\n Ailuropoda melanoleuca',
 389: 'barracouta\n snoek',
 390: 'eel',
 391: 'coho\n cohoe\n coho salmon\n blue jack\n silver salmon\n Oncorhynchus kisutch',
 392: 'rock beauty\n Holocanthus tricolor',
 393: 'anemone fish',
 394: 'sturgeon',
 395: 'gar\n garfish\n garpike\n billfish\n Lepisosteus osseus',
 396: 'lionfish',
 397: 'puffer\n pufferfish\n blowfish\n globefish',
 398: 'abacus',
 399: 'abaya',
 400: "academic gown\n academic robe\n judge's robe",
 401: 'accordion\n piano accordion\n squeeze box',
 402: 'acoustic guitar',
 403: 'aircraft carrier\n carrier\n flattop\n attack aircraft carrier',
 404: 'airliner',
 405: 'airship\n dirigible',
 406: 'altar',
 407: 'ambulance',
 408: 'amphibian\n amphibious vehicle',
 409: 'analog clock',
 410: 'apiary\n bee house',
 411: 'apron',
 412: 'ashcan\n trash can\n garbage can\n wastebin\n ash bin\n ash-bin\n ashbin\n dustbin\n trash barrel\n trash bin',
 413: 'assault rifle\n assault gun',
 414: 'backpack\n back pack\n knapsack\n packsack\n rucksack\n haversack',
 415: 'bakery\n bakeshop\n bakehouse',
 416: 'balance beam\n beam',
 417: 'balloon',
 418: 'ballpoint\n ballpoint pen\n ballpen\n Biro',
 419: 'Band Aid',
 420: 'banjo',
 421: 'bannister\n banister\n balustrade\n balusters\n handrail',
 422: 'barbell',
 423: 'barber chair',
 424: 'barbershop',
 425: 'barn',
 426: 'barometer',
 427: 'barrel\n cask',
 428: 'barrow\n garden cart\n lawn cart\n wheelbarrow',
 429: 'baseball',
 430: 'basketball',
 431: 'bassinet',
 432: 'bassoon',
 433: 'bathing cap\n swimming cap',
 434: 'bath towel',
 435: 'bathtub\n bathing tub\n bath\n tub',
 436: 'beach wagon\n station wagon\n wagon\n estate car\n beach waggon\n station waggon\n waggon',
 437: 'beacon\n lighthouse\n beacon light\n pharos',
 438: 'beaker',
 439: 'bearskin\n busby\n shako',
 440: 'beer bottle',
 441: 'beer glass',
 442: 'bell cote\n bell cot',
 443: 'bib',
 444: 'bicycle-built-for-two\n tandem bicycle\n tandem',
 445: 'bikini\n two-piece',
 446: 'binder\n ring-binder',
 447: 'binoculars\n field glasses\n opera glasses',
 448: 'birdhouse',
 449: 'boathouse',
 450: 'bobsled\n bobsleigh\n bob',
 451: 'bolo tie\n bolo\n bola tie\n bola',
 452: 'bonnet\n poke bonnet',
 453: 'bookcase',
 454: 'bookshop\n bookstore\n bookstall',
 455: 'bottlecap',
 456: 'bow',
 457: 'bow tie\n bow-tie\n bowtie',
 458: 'brass\n memorial tablet\n plaque',
 459: 'brassiere\n bra\n bandeau',
 460: 'breakwater\n groin\n groyne\n mole\n bulwark\n seawall\n jetty',
 461: 'breastplate\n aegis\n egis',
 462: 'broom',
 463: 'bucket\n pail',
 464: 'buckle',
 465: 'bulletproof vest',
 466: 'bullet train\n bullet',
 467: 'butcher shop\n meat market',
 468: 'cab\n hack\n taxi\n taxicab',
 469: 'caldron\n cauldron',
 470: 'candle\n taper\n wax light',
 471: 'cannon',
 472: 'canoe',
 473: 'can opener\n tin opener',
 474: 'cardigan',
 475: 'car mirror',
 476: 'carousel\n carrousel\n merry-go-round\n roundabout\n whirligig',
 477: "carpenter's kit\n tool kit",
 478: 'carton',
 479: 'car wheel',
 480: 'cash machine\n cash dispenser\n automated teller machine\n automatic teller machine\n automated teller\n automatic teller\n ATM',
 481: 'cassette',
 482: 'cassette player',
 483: 'castle',
 484: 'catamaran',
 485: 'CD player',
 486: 'cello\n violoncello',
 487: 'cellular telephone\n cellular phone\n cellphone\n cell\n mobile phone',
 488: 'chain',
 489: 'chainlink fence',
 490: 'chain mail\n ring mail\n mail\n chain armor\n chain armour\n ring armor\n ring armour',
 491: 'chain saw\n chainsaw',
 492: 'chest',
 493: 'chiffonier\n commode',
 494: 'chime\n bell\n gong',
 495: 'china cabinet\n china closet',
 496: 'Christmas stocking',
 497: 'church\n church building',
 498: 'cinema\n movie theater\n movie theatre\n movie house\n picture palace',
 499: 'cleaver\n meat cleaver\n chopper',
 500: 'cliff dwelling',
 501: 'cloak',
 502: 'clog\n geta\n patten\n sabot',
 503: 'cocktail shaker',
 504: 'coffee mug',
 505: 'coffeepot',
 506: 'coil\n spiral\n volute\n whorl\n helix',
 507: 'combination lock',
 508: 'computer keyboard\n keypad',
 509: 'confectionery\n confectionary\n candy store',
 510: 'container ship\n containership\n container vessel',
 511: 'convertible',
 512: 'corkscrew\n bottle screw',
 513: 'cornet\n horn\n trumpet\n trump',
 514: 'cowboy boot',
 515: 'cowboy hat\n ten-gallon hat',
 516: 'cradle',
 517: 'crane',
 518: 'crash helmet',
 519: 'crate',
 520: 'crib\n cot',
 521: 'Crock Pot',
 522: 'croquet ball',
 523: 'crutch',
 524: 'cuirass',
 525: 'dam\n dike\n dyke',
 526: 'desk',
 527: 'desktop computer',
 528: 'dial telephone\n dial phone',
 529: 'diaper\n nappy\n napkin',
 530: 'digital clock',
 531: 'digital watch',
 532: 'dining table\n board',
 533: 'dishrag\n dishcloth',
 534: 'dishwasher\n dish washer\n dishwashing machine',
 535: 'disk brake\n disc brake',
 536: 'dock\n dockage\n docking facility',
 537: 'dogsled\n dog sled\n dog sleigh',
 538: 'dome',
 539: 'doormat\n welcome mat',
 540: 'drilling platform\n offshore rig',
 541: 'drum\n membranophone\n tympan',
 542: 'drumstick',
 543: 'dumbbell',
 544: 'Dutch oven',
 545: 'electric fan\n blower',
 546: 'electric guitar',
 547: 'electric locomotive',
 548: 'entertainment center',
 549: 'envelope',
 550: 'espresso maker',
 551: 'face powder',
 552: 'feather boa\n boa',
 553: 'file\n file cabinet\n filing cabinet',
 554: 'fireboat',
 555: 'fire engine\n fire truck',
 556: 'fire screen\n fireguard',
 557: 'flagpole\n flagstaff',
 558: 'flute\n transverse flute',
 559: 'folding chair',
 560: 'football helmet',
 561: 'forklift',
 562: 'fountain',
 563: 'fountain pen',
 564: 'four-poster',
 565: 'freight car',
 566: 'French horn\n horn',
 567: 'frying pan\n frypan\n skillet',
 568: 'fur coat',
 569: 'garbage truck\n dustcart',
 570: 'gasmask\n respirator\n gas helmet',
 571: 'gas pump\n gasoline pump\n petrol pump\n island dispenser',
 572: 'goblet',
 573: 'go-kart',
 574: 'golf ball',
 575: 'golfcart\n golf cart',
 576: 'gondola',
 577: 'gong\n tam-tam',
 578: 'gown',
 579: 'grand piano\n grand',
 580: 'greenhouse\n nursery\n glasshouse',
 581: 'grille\n radiator grille',
 582: 'grocery store\n grocery\n food market\n market',
 583: 'guillotine',
 584: 'hair slide',
 585: 'hair spray',
 586: 'half track',
 587: 'hammer',
 588: 'hamper',
 589: 'hand blower\n blow dryer\n blow drier\n hair dryer\n hair drier',
 590: 'hand-held computer\n hand-held microcomputer',
 591: 'handkerchief\n hankie\n hanky\n hankey',
 592: 'hard disc\n hard disk\n fixed disk',
 593: 'harmonica\n mouth organ\n harp\n mouth harp',
 594: 'harp',
 595: 'harvester\n reaper',
 596: 'hatchet',
 597: 'holster',
 598: 'home theater\n home theatre',
 599: 'honeycomb',
 600: 'hook\n claw',
 601: 'hoopskirt\n crinoline',
 602: 'horizontal bar\n high bar',
 603: 'horse cart\n horse-cart',
 604: 'hourglass',
 605: 'iPod',
 606: 'iron\n smoothing iron',
 607: "jack-o'-lantern",
 608: 'jean\n blue jean\n denim',
 609: 'jeep\n landrover',
 610: 'jersey\n T-shirt\n tee shirt',
 611: 'jigsaw puzzle',
 612: 'jinrikisha\n ricksha\n rickshaw',
 613: 'joystick',
 614: 'kimono',
 615: 'knee pad',
 616: 'knot',
 617: 'lab coat\n laboratory coat',
 618: 'ladle',
 619: 'lampshade\n lamp shade',
 620: 'laptop\n laptop computer',
 621: 'lawn mower\n mower',
 622: 'lens cap\n lens cover',
 623: 'letter opener\n paper knife\n paperknife',
 624: 'library',
 625: 'lifeboat',
 626: 'lighter\n light\n igniter\n ignitor',
 627: 'limousine\n limo',
 628: 'liner\n ocean liner',
 629: 'lipstick\n lip rouge',
 630: 'Loafer',
 631: 'lotion',
 632: 'loudspeaker\n speaker\n speaker unit\n loudspeaker system\n speaker system',
 633: "loupe\n jeweler's loupe",
 634: 'lumbermill\n sawmill',
 635: 'magnetic compass',
 636: 'mailbag\n postbag',
 637: 'mailbox\n letter box',
 638: 'maillot',
 639: 'maillot\n tank suit',
 640: 'manhole cover',
 641: 'maraca',
 642: 'marimba\n xylophone',
 643: 'mask',
 644: 'matchstick',
 645: 'maypole',
 646: 'maze\n labyrinth',
 647: 'measuring cup',
 648: 'medicine chest\n medicine cabinet',
 649: 'megalith\n megalithic structure',
 650: 'microphone\n mike',
 651: 'microwave\n microwave oven',
 652: 'military uniform',
 653: 'milk can',
 654: 'minibus',
 655: 'miniskirt\n mini',
 656: 'minivan',
 657: 'missile',
 658: 'mitten',
 659: 'mixing bowl',
 660: 'mobile home\n manufactured home',
 661: 'Model T',
 662: 'modem',
 663: 'monastery',
 664: 'monitor',
 665: 'moped',
 666: 'mortar',
 667: 'mortarboard',
 668: 'mosque',
 669: 'mosquito net',
 670: 'motor scooter\n scooter',
 671: 'mountain bike\n all-terrain bike\n off-roader',
 672: 'mountain tent',
 673: 'mouse\n computer mouse',
 674: 'mousetrap',
 675: 'moving van',
 676: 'muzzle',
 677: 'nail',
 678: 'neck brace',
 679: 'necklace',
 680: 'nipple',
 681: 'notebook\n notebook computer',
 682: 'obelisk',
 683: 'oboe\n hautboy\n hautbois',
 684: 'ocarina\n sweet potato',
 685: 'odometer\n hodometer\n mileometer\n milometer',
 686: 'oil filter',
 687: 'organ\n pipe organ',
 688: 'oscilloscope\n scope\n cathode-ray oscilloscope\n CRO',
 689: 'overskirt',
 690: 'oxcart',
 691: 'oxygen mask',
 692: 'packet',
 693: 'paddle\n boat paddle',
 694: 'paddlewheel\n paddle wheel',
 695: 'padlock',
 696: 'paintbrush',
 697: "pajama\n pyjama\n pj's\n jammies",
 698: 'palace',
 699: 'panpipe\n pandean pipe\n syrinx',
 700: 'paper towel',
 701: 'parachute\n chute',
 702: 'parallel bars\n bars',
 703: 'park bench',
 704: 'parking meter',
 705: 'passenger car\n coach\n carriage',
 706: 'patio\n terrace',
 707: 'pay-phone\n pay-station',
 708: 'pedestal\n plinth\n footstall',
 709: 'pencil box\n pencil case',
 710: 'pencil sharpener',
 711: 'perfume\n essence',
 712: 'Petri dish',
 713: 'photocopier',
 714: 'pick\n plectrum\n plectron',
 715: 'pickelhaube',
 716: 'picket fence\n paling',
 717: 'pickup\n pickup truck',
 718: 'pier',
 719: 'piggy bank\n penny bank',
 720: 'pill bottle',
 721: 'pillow',
 722: 'ping-pong ball',
 723: 'pinwheel',
 724: 'pirate\n pirate ship',
 725: 'pitcher\n ewer',
 726: "plane\n carpenter's plane\n woodworking plane",
 727: 'planetarium',
 728: 'plastic bag',
 729: 'plate rack',
 730: 'plow\n plough',
 731: "plunger\n plumber's helper",
 732: 'Polaroid camera\n Polaroid Land camera',
 733: 'pole',
 734: 'police van\n police wagon\n paddy wagon\n patrol wagon\n wagon\n black Maria',
 735: 'poncho',
 736: 'pool table\n billiard table\n snooker table',
 737: 'pop bottle\n soda bottle',
 738: 'pot\n flowerpot',
 739: "potter's wheel",
 740: 'power drill',
 741: 'prayer rug\n prayer mat',
 742: 'printer',
 743: 'prison\n prison house',
 744: 'projectile\n missile',
 745: 'projector',
 746: 'puck\n hockey puck',
 747: 'punching bag\n punch bag\n punching ball\n punchball',
 748: 'purse',
 749: 'quill\n quill pen',
 750: 'quilt\n comforter\n comfort\n puff',
 751: 'racer\n race car\n racing car',
 752: 'racket\n racquet',
 753: 'radiator',
 754: 'radio\n wireless',
 755: 'radio telescope\n radio reflector',
 756: 'rain barrel',
 757: 'recreational vehicle\n RV\n R.V.',
 758: 'reel',
 759: 'reflex camera',
 760: 'refrigerator\n icebox',
 761: 'remote control\n remote',
 762: 'restaurant\n eating house\n eating place\n eatery',
 763: 'revolver\n six-gun\n six-shooter',
 764: 'rifle',
 765: 'rocking chair\n rocker',
 766: 'rotisserie',
 767: 'rubber eraser\n rubber\n pencil eraser',
 768: 'rugby ball',
 769: 'rule\n ruler',
 770: 'running shoe',
 771: 'safe',
 772: 'safety pin',
 773: 'saltshaker\n salt shaker',
 774: 'sandal',
 775: 'sarong',
 776: 'sax\n saxophone',
 777: 'scabbard',
 778: 'scale\n weighing machine',
 779: 'school bus',
 780: 'schooner',
 781: 'scoreboard',
 782: 'screen\n CRT screen',
 783: 'screw',
 784: 'screwdriver',
 785: 'seat belt\n seatbelt',
 786: 'sewing machine',
 787: 'shield\n buckler',
 788: 'shoe shop\n shoe-shop\n shoe store',
 789: 'shoji',
 790: 'shopping basket',
 791: 'shopping cart',
 792: 'shovel',
 793: 'shower cap',
 794: 'shower curtain',
 795: 'ski',
 796: 'ski mask',
 797: 'sleeping bag',
 798: 'slide rule\n slipstick',
 799: 'sliding door',
 800: 'slot\n one-armed bandit',
 801: 'snorkel',
 802: 'snowmobile',
 803: 'snowplow\n snowplough',
 804: 'soap dispenser',
 805: 'soccer ball',
 806: 'sock',
 807: 'solar dish\n solar collector\n solar furnace',
 808: 'sombrero',
 809: 'soup bowl',
 810: 'space bar',
 811: 'space heater',
 812: 'space shuttle',
 813: 'spatula',
 814: 'speedboat',
 815: "spider web\n spider's web",
 816: 'spindle',
 817: 'sports car\n sport car',
 818: 'spotlight\n spot',
 819: 'stage',
 820: 'steam locomotive',
 821: 'steel arch bridge',
 822: 'steel drum',
 823: 'stethoscope',
 824: 'stole',
 825: 'stone wall',
 826: 'stopwatch\n stop watch',
 827: 'stove',
 828: 'strainer',
 829: 'streetcar\n tram\n tramcar\n trolley\n trolley car',
 830: 'stretcher',
 831: 'studio couch\n day bed',
 832: 'stupa\n tope',
 833: 'submarine\n pigboat\n sub\n U-boat',
 834: 'suit\n suit of clothes',
 835: 'sundial',
 836: 'sunglass',
 837: 'sunglasses\n dark glasses\n shades',
 838: 'sunscreen\n sunblock\n sun blocker',
 839: 'suspension bridge',
 840: 'swab\n swob\n mop',
 841: 'sweatshirt',
 842: 'swimming trunks\n bathing trunks',
 843: 'swing',
 844: 'switch\n electric switch\n electrical switch',
 845: 'syringe',
 846: 'table lamp',
 847: 'tank\n army tank\n armored combat vehicle\n armoured combat vehicle',
 848: 'tape player',
 849: 'teapot',
 850: 'teddy\n teddy bear',
 851: 'television\n television system',
 852: 'tennis ball',
 853: 'thatch\n thatched roof',
 854: 'theater curtain\n theatre curtain',
 855: 'thimble',
 856: 'thresher\n thrasher\n threshing machine',
 857: 'throne',
 858: 'tile roof',
 859: 'toaster',
 860: 'tobacco shop\n tobacconist shop\n tobacconist',
 861: 'toilet seat',
 862: 'torch',
 863: 'totem pole',
 864: 'tow truck\n tow car\n wrecker',
 865: 'toyshop',
 866: 'tractor',
 867: 'trailer truck\n tractor trailer\n trucking rig\n rig\n articulated lorry\n semi',
 868: 'tray',
 869: 'trench coat',
 870: 'tricycle\n trike\n velocipede',
 871: 'trimaran',
 872: 'tripod',
 873: 'triumphal arch',
 874: 'trolleybus\n trolley coach\n trackless trolley',
 875: 'trombone',
 876: 'tub\n vat',
 877: 'turnstile',
 878: 'typewriter keyboard',
 879: 'umbrella',
 880: 'unicycle\n monocycle',
 881: 'upright\n upright piano',
 882: 'vacuum\n vacuum cleaner',
 883: 'vase',
 884: 'vault',
 885: 'velvet',
 886: 'vending machine',
 887: 'vestment',
 888: 'viaduct',
 889: 'violin\n fiddle',
 890: 'volleyball',
 891: 'waffle iron',
 892: 'wall clock',
 893: 'wallet\n billfold\n notecase\n pocketbook',
 894: 'wardrobe\n closet\n press',
 895: 'warplane\n military plane',
 896: 'washbasin\n handbasin\n washbowl\n lavabo\n wash-hand basin',
 897: 'washer\n automatic washer\n washing machine',
 898: 'water bottle',
 899: 'water jug',
 900: 'water tower',
 901: 'whiskey jug',
 902: 'whistle',
 903: 'wig',
 904: 'window screen',
 905: 'window shade',
 906: 'Windsor tie',
 907: 'wine bottle',
 908: 'wing',
 909: 'wok',
 910: 'wooden spoon',
 911: 'wool\n woolen\n woollen',
 912: 'worm fence\n snake fence\n snake-rail fence\n Virginia fence',
 913: 'wreck',
 914: 'yawl',
 915: 'yurt',
 916: 'web site\n website\n internet site\n site',
 917: 'comic book',
 918: 'crossword puzzle\n crossword',
 919: 'street sign',
 920: 'traffic light\n traffic signal\n stoplight',
 921: 'book jacket\n dust cover\n dust jacket\n dust wrapper',
 922: 'menu',
 923: 'plate',
 924: 'guacamole',
 925: 'consomme',
 926: 'hot pot\n hotpot',
 927: 'trifle',
 928: 'ice cream\n icecream',
 929: 'ice lolly\n lolly\n lollipop\n popsicle',
 930: 'French loaf',
 931: 'bagel\n beigel',
 932: 'pretzel',
 933: 'cheeseburger',
 934: 'hotdog\n hot dog\n red hot',
 935: 'mashed potato',
 936: 'head cabbage',
 937: 'broccoli',
 938: 'cauliflower',
 939: 'zucchini\n courgette',
 940: 'spaghetti squash',
 941: 'acorn squash',
 942: 'butternut squash',
 943: 'cucumber\n cuke',
 944: 'artichoke\n globe artichoke',
 945: 'bell pepper',
 946: 'cardoon',
 947: 'mushroom',
 948: 'Granny Smith',
 949: 'strawberry',
 950: 'orange',
 951: 'lemon',
 952: 'fig',
 953: 'pineapple\n ananas',
 954: 'banana',
 955: 'jackfruit\n jak\n jack',
 956: 'custard apple',
 957: 'pomegranate',
 958: 'hay',
 959: 'carbonara',
 960: 'chocolate sauce\n chocolate syrup',
 961: 'dough',
 962: 'meat loaf\n meatloaf',
 963: 'pizza\n pizza pie',
 964: 'potpie',
 965: 'burrito',
 966: 'red wine',
 967: 'espresso',
 968: 'cup',
 969: 'eggnog',
 970: 'alp',
 971: 'bubble',
 972: 'cliff\n drop\n drop-off',
 973: 'coral reef',
 974: 'geyser',
 975: 'lakeside\n lakeshore',
 976: 'promontory\n headland\n head\n foreland',
 977: 'sandbar\n sand bar',
 978: 'seashore\n coast\n seacoast\n sea-coast',
 979: 'valley\n vale',
 980: 'volcano',
 981: 'ballplayer\n baseball player',
 982: 'groom\n bridegroom',
 983: 'scuba diver',
 984: 'rapeseed',
 985: 'daisy',
 986: "yellow lady's slipper\n yellow lady-slipper\n Cypripedium calceolus\n Cypripedium parviflorum",
 987: 'corn',
 988: 'acorn',
 989: 'hip\n rose hip\n rosehip',
 990: 'buckeye\n horse chestnut\n conker',
 991: 'coral fungus',
 992: 'agaric',
 993: 'gyromitra',
 994: 'stinkhorn\n carrion fungus',
 995: 'earthstar',
 996: 'hen-of-the-woods\n hen of the woods\n Polyporus frondosus\n Grifola frondosa',
 997: 'bolete',
 998: 'ear\n spike\n capitulum',
 999: 'toilet tissue\n toilet paper\n bathroom tissue'}

图片识别

 

python app.py
Input the path and image name:pic/b.jpg
/home/chi/anaconda3/lib/python3.6/site-packages/skimage/transform/_warps.py:105: UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15.
  warn("The default mode, 'constant', will be changed to 'reflect' in "
/home/chi/anaconda3/lib/python3.6/site-packages/skimage/transform/_warps.py:110: UserWarning: Anti-aliasing will be enabled by default in skimage 0.15 to avoid aliasing artifacts when down-sampling images.
  warn("Anti-aliasing will be enabled by default in skimage 0.15 to "
img_ready shape [  1 224 224   3]
/home/chi/tf/vgg/vgg16.npy
conv5_1
fc6
conv5_3
conv5_2
fc8
fc7
conv4_1
conv4_2
conv4_3
conv3_3
conv3_2
conv3_1
conv1_1
conv1_2
conv2_2
conv2_1
build model started
time consuming: 0.665246
top5: [345 690 339 730 719]
n: 0
i: 345
345 : ox ---- 81.98%
n: 1
i: 690
690 : oxcart ---- 6.35%
n: 2
i: 339
339 : sorrel ---- 4.20%
n: 3
i: 730
730 : plow
 plough ---- 1.25%
n: 4
i: 719
719 : piggy bank
 penny bank ---- 0.97%
/home/chi/anaconda3/lib/python3.6/site-packages/matplotlib/font_manager.py:1328: UserWarning: findfont: Font family ['sans-serif'] not found. Falling back to DejaVu Sans
  (prop.get_family(), self.defaultFamily[fontext]))

没有更多推荐了,返回首页