caffe-ubuntu1604-gtx850m-i7-4710hq----bvlc_reference_caffenet.caffemodel
bvlc_reference_caffenet.caffemodel
---
name: BAIR/BVLC CaffeNet Model
caffemodel: bvlc_reference_caffenet.caffemodel
caffemodel_url: http://dl.caffe.berkeleyvision.org/bvlc_reference_caffenet.caffemodel
license: unrestricted
sha1: 4c8d77deb20ea792f84eb5e6d0a11ca0a8660a46
caffe_commit: 709dc15af4a06bebda027c1eb2b3f3e3375d5077
--- This model is the result of following the Caffe [ImageNet model training instructions](http://caffe.berkeleyvision.org/gathered/examples/imagenet.html).
It is a replication of the model described in the [AlexNet](http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks) publication with some differences: - not training with the relighting data-augmentation;
- the order of pooling and normalization layers is switched (in CaffeNet, pooling is done before normalization). This model is snapshot of iteration 310,000.
The best validation performance during training was iteration 313,000 with validation accuracy 57.412% and loss 1.82328.
This model obtains a top-1 accuracy 57.4% and a top-5 accuracy 80.4% on the validation set, using just the center crop.
(Using the average of 10 crops, (4 + 1 center) * 2 mirror, should obtain a bit higher accuracy still.) This model was trained by Jeff Donahue @jeffdonahue ## License This model is released for unrestricted use.
whale@sea:/media/whale/wsWin10/wsUbuntu16.04/DlFrames/caffe$ ./build/install/bin/classification \
> /media/whale/wsWin10/wsUbuntu16.04/DlFrames/caffe/models/bvlc_reference_caffenet/deploy.prototxt \
> /media/whale/wsWin10/wsUbuntu16.04/DlFrames/caffe/models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel \
> data/ilsvrc12/imagenet_mean.binaryproto \
> /media/whale/wsWin10/wsCaffe/model-zoo/VGG16/synset_words.txt \
> /media/whale/wsWin10/images/person/2.jpg
labels_.size() = 1000 output_layer->channels() = 1000 ---------- Prediction for /media/whale/wsWin10/images/person/2.jpg ----------
0.3411 - "n03676483 lipstick, lip rouge"
0.1024 - "n03325584 feather boa, boa"
0.0978 - "n07615774 ice lolly, lolly, lollipop, popsicle"
0.0734 - "n02786058 Band Aid"
0.0601 - "n04357314 sunscreen, sunblock, sun blocker" 翻译: 口红,口红
whale@sea:/media/whale/wsWin10/wsUbuntu16.04/DlFrames/caffe$ ./build/install/bin/classification \
> /media/whale/wsWin10/wsUbuntu16.04/DlFrames/caffe/models/bvlc_reference_caffenet/deploy.prototxt \
> /media/whale/wsWin10/wsUbuntu16.04/DlFrames/caffe/models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel \
> data/ilsvrc12/imagenet_mean.binaryproto \
> /media/whale/wsWin10/wsCaffe/model-zoo/VGG16/synset_words.txt \
> /media/whale/wsWin10/images/person/3.jpg
labels_.size() = 1000 output_layer->channels() = 1000 ---------- Prediction for /media/whale/wsWin10/images/person/3.jpg ----------
0.4030 - "n02883205 bow tie, bow-tie, bowtie"
0.3799 - "n04350905 suit, suit of clothes"
0.0473 - "n02865351 bolo tie, bolo, bola tie, bola"
0.0131 - "n04591157 Windsor tie"
0.0114 - "n02786058 Band Aid"
领结,领带,领结
caffe-ubuntu1604-gtx850m-i7-4710hq----bvlc_reference_caffenet.caffemodel的更多相关文章
- bvlc_reference_caffenet.caffemodel
#uncoding:utf-8 # set up Python environment: numpy for numerical routines, and matplotlib for plotti ...
- Caffe学习系列(20):用训练好的caffemodel来进行分类
caffe程序自带有一张小猫图片,存放路径为caffe根目录下的 examples/images/cat.jpg, 如果我们想用一个训练好的caffemodel来对这张图片进行分类,那该怎么办呢? 如 ...
- 【转】Caffe初试(十)命令行解析
caffe的运行提供三种接口:C++接口(命令行).Python接口和matlab接口.本文先对命令行进行解析,后续会依次介绍其它两种接口. caffe的C++主程序(caffe.cpp)放在根目录下 ...
- Caffe框架下的图像回归测试
Caffe框架下的图像回归测试 参考资料: 1. http://stackoverflow.com/questions/33766689/caffe-hdf5-pre-processing 2. ht ...
- Caffe fine-tuning 微调网络
转载请注明出处,楼燚(yì)航的blog,http://www.cnblogs.com/louyihang-loves-baiyan/ 目前呢,caffe,theano,torch是当下比较流行的De ...
- Caffe学习系列(23):如何将别人训练好的model用到自己的数据上
caffe团队用imagenet图片进行训练,迭代30多万次,训练出来一个model.这个model将图片分为1000类,应该是目前为止最好的图片分类model了. 假设我现在有一些自己的图片想进行分 ...
- caffe使用
训练时, solver.prototxt中使用的是train_val.prototxt ./build/tools/caffe/train -solver ./models/bvlc_referenc ...
- 71 mac boook pro 无 gpu 下caffe 安装
71 mac boook pro 无 gpu 下caffe 安装 1.首先安装homebrew工具,相当于Mac下的yum或apt ruby -e "$(curl -fsSL https:/ ...
- Caffe学习系列(13):对训练好的模型进行fine-tune
使用http://www.cnblogs.com/573177885qq/p/5804863.html中的图片进行训练和测试. 整个流程差不多,fine-tune命令: ./build/tools/c ...
- Caffe学习系列(10):命令行解析
训练网络命令: sudo sh ./build/tools/caffe train --solver=examples/mnist/train_lenet.sh 用预先训练好的权重来fine-tuni ...
随机推荐
- UVa 11234 The Largest Clique
找最长的连接的点的数量.用tarjan缩点,思考可知每一个强连通分量里的点要么都选,要么都不选(走别的路),可以动规解决. #include<iostream> #include<c ...
- .net反编译工具Reflector下载(转)
原文发布时间为:2010-10-23 -- 来源于本人的百度文章 [由搬家工具导入] 打开Reflector工具并且下载了一个FileDisassembler插件,FileDisassembler插件 ...
- VBCodeProvider .net compiler service interface or something like that
https://msdn.microsoft.com/zh-cn/library/microsoft.visualbasic.vbcodeprovider%28v=vs.110%29.aspx ref ...
- Android开发跳坑记录
本文主要记录在Android开发中遇见的一些问题,以及解决方法. 2015.12.01 1.adb.exe 端口被占用 解决: http://blog.csdn.net/xiaanming/artic ...
- RecyclerView的Item和Item内的控件点击处理
需求场景:RecyclerView的Item需要点击,或者Item中的某个控件需要点击,或者两者同时需要点击处理. 一.adapter代码如下: package com.ldw.adapter; im ...
- iOS直播Liveroom组件,游客,用户多次切换登录同一直播间,消息出现多次重复问题解决
byzqk 新版,加入连麦功能,直播的流程修改很多,每次登录都需要登录liveroom组件 期间遇到一个奇葩的问题,就是游客登录组件之后,切换为用户登录,出现im消息重复的问题,一开始以为是游客退出不 ...
- ABP开发框架前后端开发系列---(3)框架的分层和文件组织
在前面随笔<ABP开发框架前后端开发系列---(2)框架的初步介绍>中,我介绍了ABP应用框架的项目组织情况,以及项目中领域层各个类代码组织,以便基于数据库应用的简化处理.本篇随笔进一步对 ...
- Git之Github使用(一):Push代码到Github
Git之Github使用(一):Push代码到Github 热度 2已有 58 次阅读2016-8-26 17:56 |个人分类:常见问题|系统分类:移动开发| 互联网, commit, status ...
- 使用 ODP.NET 访问 Oracle(.net如何访问Oracle)详解【转】
http://www.cnblogs.com/qinpengming/archive/2013/06/08/3127346.html 1,什么是ODF .NE,?就是Oracle 为 .NET (OD ...
- 高校师生福利!从现在起,可以免费申请LocaSpace和Wish3D的SDK!
目前,以管理空间数据见长的GIS已经在全球变化与监测.军事.资源管理.城市规划.土地管理.环境研究.灾害预测.交通管理.文物保护以及政府部门等许多领域发挥着越来越重要的作用. 如何开发出功能丰富又简洁 ...