Caffe中HDF5Data例子
来源:互联网 发布:魅族6手机备份数据 编辑:程序博客网 时间:2024/06/17 03:18
- Caffe中HDF5Data用于处理多标签数据,例子如下:
name: "LeNet"###for data and labelslayer { name: "data" type: "HDF5Data" top: "data" top: "labels" include { phase: TRAIN } hdf5_data_param { source: "list_train.txt" batch_size: 100 }}layer { name: "data" type: "HDF5Data" top: "data" top: "labels" include { phase: TEST } hdf5_data_param { source: "list_test.txt" batch_size: 100 }}layer { name: "slicers" type: "Slice" bottom: "labels" top: "label_1" top: "label_2" slice_param { axis: 1 slice_point: 1 }}### for alllayer { name: "conv_all" type: "Convolution" bottom: "data" top: "conv_all" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 50 kernel_size: 5 stride: 1 weight_filler { type: "xavier" } bias_filler { type: "constant" } }}layer { name: "relu_all" type: "ReLU" bottom: "conv_all" top: "conv_all"}layer { name: "pool_all" type: "Pooling" bottom: "conv_all" top: "pool_all" pooling_param { pool: MAX kernel_size: 2 stride: 2 }}### for kind_1layer { name: "ip1" type: "InnerProduct" bottom: "pool_all" top: "ip1" param { lr_mult: 1 } param { lr_mult: 2 } inner_product_param { num_output: 2 weight_filler { type: "xavier" } bias_filler { type: "constant" } }}layer { name: "accuracy1" type: "Accuracy" bottom: "ip1" bottom: "label_1" top: "accuracy1" include { phase: TEST }}layer { name: "loss_1" type: "SoftmaxWithLoss" bottom: "ip1" bottom: "label_1" top: "loss_1"}###for kind_2layer { name: "ip2" type: "InnerProduct" bottom: "pool_all" top: "ip2" param { lr_mult: 1 } param { lr_mult: 2 } inner_product_param { num_output: 3 weight_filler { type: "xavier" } bias_filler { type: "constant" } }}layer { name: "accuracy2" type: "Accuracy" bottom: "ip2" bottom: "label_2" top: "accuracy2" include { phase: TEST }}layer { name: "loss_2" type: "SoftmaxWithLoss" bottom: "ip2" bottom: "label_2" top: "loss_2"}
- 注:如何生成hdf5文件,详见:生成hdf5文件用于多标签训练
- 注:Hdf5Data详见:HDF5 Input
- 注:Slice详见:Slicing
- 最终网络结构如下图:
- 注:Caffe学习:使用pycaffe绘制网络结构
0 1
- Caffe中HDF5Data例子
- Caffe中HDF5Data例子
- caffe HDF5Data 层使用及数据生成
- caffe HDF5Data 层使用及数据生成
- caffe HDF5Data 层使用及数据生成
- caffe学习笔记(11):多任务学习之HDF5Data类型数据集生成
- Caffe中mnist例子(一)自定义输入层
- cnn shuffle hdf5data
- caffe例子mnist
- caffe例子mnist
- caffe分类小例子
- Caffe自带例子运行
- caffe官网教程中siamese例子,画特征错误提示及解决办法
- [记录caffe学习]1.caffe自带数字识别例子
- Caffe(3):运行caffe自带的两个简单例子
- Caffe代码导读(1):Protobuf例子
- Caffe代码导读(1):Protobuf例子
- Caffe代码导读(1):Protobuf例子
- ubuntu firefox install flash
- iOS线程安全
- Spring+Quartz 从数据库中获取定时任务和定时时间,动态实现对定时任务的增删改查
- MySQL创建用户与授权方法
- iOS KVO和KVC及广播
- Caffe中HDF5Data例子
- j2ee开发环境的建立(按需更新)
- iOS多线程
- java学习_多线程2和设计模式
- linux内存管理之kmalloc
- LeetCode_LinkedList_Easy
- 例题5.8 最大团 UVa11324
- iOS-GCD常用代码小结
- Visual Studio 2012 编译错误【error C4996: 'scanf': This function or variable may be unsafe. 】的解决方案