caffe 实践程序4——cifar10网络
来源:互联网 发布:linux patsubst 编辑:程序博客网 时间:2024/06/06 00:23
cifar10是个中小型的图片数据库,总共60000张32*32大小的图片,5w张用于训练,1w张用于测试。
caffe上cifar10的训练流程。
cifar10_quick_train_test.prototxt
name: "CIFAR10_quick"layer { name: "cifar" type: "Data" top: "data" top: "label" include { phase: TRAIN } transform_param { mean_file: "examples/cifar10/mean.binaryproto" } data_param { source: "examples/cifar10/cifar10_train_lmdb" batch_size: 100 backend: LMDB }}layer { name: "cifar" type: "Data" top: "data" top: "label" include { phase: TEST } transform_param { mean_file: "examples/cifar10/mean.binaryproto" } data_param { source: "examples/cifar10/cifar10_test_lmdb" batch_size: 100 backend: LMDB }}layer { name: "conv1" type: "Convolution" bottom: "data" top: "conv1" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 32 pad: 2 kernel_size: 5 stride: 1 weight_filler { type: "gaussian" std: 0.0001 } bias_filler { type: "constant" } }}layer { name: "pool1" type: "Pooling" bottom: "conv1" top: "pool1" pooling_param { pool: MAX kernel_size: 3 stride: 2 }}layer { name: "relu1" type: "ReLU" bottom: "pool1" top: "pool1"}layer { name: "conv2" type: "Convolution" bottom: "pool1" top: "conv2" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 32 pad: 2 kernel_size: 5 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" } }}layer { name: "relu2" type: "ReLU" bottom: "conv2" top: "conv2"}layer { name: "pool2" type: "Pooling" bottom: "conv2" top: "pool2" pooling_param { pool: AVE kernel_size: 3 stride: 2 }}layer { name: "conv3" type: "Convolution" bottom: "pool2" top: "conv3" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 64 pad: 2 kernel_size: 5 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" } }}layer { name: "relu3" type: "ReLU" bottom: "conv3" top: "conv3"}layer { name: "pool3" type: "Pooling" bottom: "conv3" top: "pool3" pooling_param { pool: AVE kernel_size: 3 stride: 2 }}layer { name: "ip1" type: "InnerProduct" bottom: "pool3" top: "ip1" param { lr_mult: 1 } param { lr_mult: 2 } inner_product_param { num_output: 64 weight_filler { type: "gaussian" std: 0.1 } bias_filler { type: "constant" } }}layer { name: "ip2" type: "InnerProduct" bottom: "ip1" top: "ip2" param { lr_mult: 1 } param { lr_mult: 2 } inner_product_param { num_output: 10 weight_filler { type: "gaussian" std: 0.1 } bias_filler { type: "constant" } }}layer { name: "accuracy" type: "Accuracy" bottom: "ip2" bottom: "label" top: "accuracy" include { phase: TEST }}layer { name: "loss" type: "SoftmaxWithLoss" bottom: "ip2" bottom: "label" top: "loss"}
之前做可视化,导师想通过改变网络层数训练模型,进而观察可视化结果,来评估网络好坏程度及为修改网络参数提供方案。
一张32*32大小的图片输入网络,变动如下:
conv1 100 32 32*32pool1 100 32 16*16conv2 100 32 16*16pool2 100 32 8*8conv3 100 64 8*8pool3 100 64 4*4ip1 100 64 1*1ip1 100 10 1*1
因为conv1中的pad参数,所以从conv1出来的大小为(32+2×pad-kernel_size+stride)/stride=32,即输入是32*32,输出也是32*32。
现在在原网络增加两大层(一个大层是指:conv,pool,relu),中间有5大层时,网络已达极限,因为原始图片为32*32大小,
网络5:data ->cpr1->crp2->crp3->crp4->crp5->ip1->ip2 识别率:53% 52.29%
若再增加层数识别率均为10%,现原因不明
0 0
- caffe 实践程序4——cifar10网络
- caffe 实践程序4——cifar10网络
- Caffe:可视化Cifar10 网络模型
- 【caffe学习笔记——cifar10】win10+caffe环境下cifar10运行
- caffe学习笔记--自定义cifar10网络参数
- caffe——cifar10模型训练自己的数据
- 深度学习之caffe入门——cifar10例程
- caffe&windows工作过程 — cifar10为例
- caffe&windows工作过程 — cifar10为例
- Caffe:cifar10
- caffe练习实例(2)——cifar10在caffe上训练学习
- caffe实践程序1——mnist任务总结
- caffe实践程序1——mnist任务总结
- caffe 实践程序2——用细分的方法实现caffe中cifar100的识别
- caffe 实践程序3——caffe提取特征以及由模型test数据
- caffe 实践程序2——用细分的方法实现caffe中cifar100的识别
- caffe 实践程序3——caffe提取特征以及由模型test数据
- 深度学习-CAFFE利用CIFAR10网络模型训练自己的图像数据获得模型-4应用生成模型进行预测
- Installing the google coding style settings in Eclipse
- 今天写代码,感觉不写代码,手就痒
- HTTP代理协议 HTTP/1.1的CONNECT方法
- discuz不支持jquery写法的解决办法
- WorkerMan 3.x 扩展安装心得
- caffe 实践程序4——cifar10网络
- 登入Tomcat Manager时出现401错误——解决方法
- vim 中OmniCppComplete的安装和使用
- discuz用到的几个函数
- Java经典书籍汇集
- [学习记录]__IPHONE_OS_VERSION_MIN_REQUIRED
- Python 解析 xml文档
- [iOS_Dev] UIWebView使用本地资源
- Ext 的confirm与window的confirm的区别