LSTM
来源:互联网 发布:手机网络时间同步软件 编辑:程序博客网 时间:2024/05/22 15:01
- name: "BasicLstm"
- layer {
- name: "data"
- type: "HDF5Data"
- top: "data" //输入数据
- top: "cont" //数据切分(不是1就是0)
- top: "label"//对应的标签
- include {
- phase: TRAIN
- }
- hdf5_data_param {
- source: "./path_to_txt.txt"
- batch_size: 2000
- }
- }
- layer {
- name: "lstm1"
- type: "LSTM"
- bottom: "data"
- bottom: "cont"
- top: "lstm1"
- recurrent_param {
- num_output: 5 //LSTM1输出的对应维度
- weight_filler {
- type: "uniform"
- min: -0.08
- max: 0.08
- }
- bias_filler {
- type: "constant"
- value: 0
- }
- }
- }
- layer {
- name: "lstm2"
- type: "LSTM"
- bottom: "lstm1"
- bottom: "cont"
- top: "lstm2"
- recurrent_param {
- num_output: 4 //LSTM2输出对应的维度
- weight_filler {
- type: "uniform"
- min: -0.08
- max: 0.08
- }
- bias_filler {
- type: "constant"
- value: 0
- }
- }
- }
- layer {
- name: "predict"
- type: "InnerProduct"
- bottom: "lstm2"
- top: "predict"
- param {
- lr_mult: 1
- decay_mult: 1
- }
- param {
- lr_mult: 2
- decay_mult: 0
- }
- inner_product_param {
- num_output: 39 //对应的输出维度用于分类
- weight_filler {
- type: "gaussian"
- std: 0.01
- }
- bias_filler {
- type: "constant"
- value: 0
- }
- axis: 2
- }
- }
- layer {
- name: "softmax_loss"
- type: "SoftmaxWithLoss" //softmax分类
- bottom: "predict"
- bottom: "label"
- top: "loss"
- loss_weight: 20
- softmax_param {
- axis: 2
- }
- loss_param {
- ignore_label: -1 //忽略标签为-1的数据
- }
- }
阅读全文
0 0
- LSTM
- lstm
- lstm
- lstm
- LSTM
- LSTM
- LSTM
- LSTM
- lstm
- lstm
- LSTM
- LSTM
- LSTM
- LSTM
- LSTM
- LSTM
- LSTM
- LSTM
- node.js
- 使用输入输出流迭代器读取和写入文件
- 2017暑期集训一Restoring Painting(思维)
- js校验页面输入是否为空
- 内存映射
- LSTM
- 2016web前端面试题
- Html5(移动端)开发,安卓机上的软键盘顶起影响页面布局
- Linux SPI总线和设备驱动架构之四:SPI数据传输的队列化
- jenkins 构建maven工程--Unknown lifecycle phase "clean"
- HDU1019
- RPC与Apache Thift
- ubuntu piix4_smbus: Host SMBus controller not enabled!解决方案
- 对linux内核的container_of和offsetof宏的理解