当我使用Caffe BP回归模型时,为什么大多数预测结果为0? [英] Why most of the predicted results are 0 when I use a Caffe BP regression model?
本文介绍了当我使用Caffe BP回归模型时,为什么大多数预测结果为0?的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!
问题描述
我将输入数据转换为hdf5格式. 每个输入数据的形状为309暗和标签 输入数据如下: 部分输入数据是这样的
I converted my input data into hdf5 format. And each input data has a shape of 309 dims and a label the input data just as follow: part of the input data like this
我的净结构如下:
name: "RegressionNet"
layer {
name: "framert"
type: "HDF5Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
hdf5_data_param {
source: "train_data_list.txt"
batch_size: 100
}
}
layer {
name: "framert"
type: "HDF5Data"
top: "data"
top: "label"
include {
phase: TEST
}
hdf5_data_param {
source: "test_data_list.txt"
batch_size: 100
}
}
layer {
name: "inner1"
type: "InnerProduct"
bottom: "data"
top: "inner1"
param {
lr_mult: 1
decay_mult: 1.5
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 500
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "inner2"
type: "InnerProduct"
bottom: "inner1"
top: "inner2"
param {
lr_mult: 1
decay_mult: 1.0
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 400
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "inner3"
type: "InnerProduct"
bottom: "inner2"
top: "inner3"
param {
lr_mult: 1
decay_mult: 1.0
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 300
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "inner4"
type: "InnerProduct"
bottom: "inner3"
top: "inner4"
param {
lr_mult: 1
decay_mult: 1.0
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 200
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "inner5"
type: "InnerProduct"
bottom: "inner4"
top: "inner5"
param {
lr_mult: 1
decay_mult: 1.0
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 100
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "inner6"
type: "InnerProduct"
bottom: "inner5"
top: "inner6"
param {
lr_mult: 1
decay_mult: 1.0
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "inner6"
top: "inner6"
relu_param {
engine: CAFFE
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "inner6"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "EuclideanLoss"
bottom: "inner6"
bottom: "label"
top: "loss"
}
我的求解器如下:
net: "net_csv_hdf5.prototxt"
test_iter: 100
test_interval: 100
base_lr: 0.001
momentum: 0.9
weight_decay: 0.0005
lr_policy: "inv"
gamma: 0.0001
power: 0.75
display: 50
max_iter: 5000
snapshot: 2500
snapshot_prefix: "/examples"
solver_mode: CPU
完成训练阶段后,我使用测试数据进行预测,而预测结果如下(零点太多):
After completing the training phase,I use the test data to predict, while the predicted result as follow(there are too many zeros):
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0.000122316
0.00318826
0.00606083
0.0092759
0.0124592
0.015264
0.0181027
0.021088
0.0237832
0.027108
0.0306765
0.0345342
0.0379068
0.0409781
0.044281
0.0478444
0.0509017
推荐答案
您忘了像这样在net.prototxt中添加激活功能"
You forget add activation function in net.prototxt like this"
layer {
name: "Sigmoid1"
type: "Sigmoid"
bottom: "inner1"
top: "Sigmoid1"
}
这篇关于当我使用Caffe BP回归模型时,为什么大多数预测结果为0?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!
查看全文