在训练一个小的分类网络时，发现加上BatchNorm层之后的检索效果相对于之前，效果会有提升，因此将该网络结构记录在这里，供以后查阅使用：
添加该层之前：
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
convolution_param {
num_output:
kernel_size:
stride:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size:
stride:
}
}
layer {
name: "norm1"
type: "LRN"
bottom: "pool1"
top: "norm1"
lrn_param {
local_size:
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "norm1"
top: "conv2"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
convolution_param {
num_output:
pad:
kernel_size:
stride:
group:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size:
stride:
}
}
layer {
name: "norm2"
type: "LRN"
bottom: "pool2"
top: "norm2"
lrn_param {
local_size:
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "norm2"
top: "conv3"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
convolution_param {
num_output:
pad:
stride:
kernel_size:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
convolution_param {
num_output:
pad:
kernel_size:
group:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
convolution_param {
num_output:
pad:
stride:
kernel_size:
group:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size:
stride:
}
}
layer {
name: "fc6_srx"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
inner_product_param {
num_output:
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value:
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7_srx"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
inner_product_param {
num_output:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
layer{
name: "loss"
type: "SoftmaxWithLoss"
top: "SoftmaxWithLoss"
bottom: "fc7"
bottom: "label"
include {
phase: TRAIN
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc7"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}添加该层之后：
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
convolution_param {
num_output:
kernel_size:
stride:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
##############
layer {
bottom: "conv1"
top: "conv1"
name: "bn1"
type: "BatchNorm"
param {
lr_mult:
}
param {
lr_mult:
}
param {
lr_mult:
}
}
##############
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size:
stride:
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
convolution_param {
num_output:
pad:
kernel_size:
stride:
group:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
##############
layer {
bottom: "conv2"
top: "conv2"
name: "bn2"
type: "BatchNorm"
param {
lr_mult:
}
param {
lr_mult:
}
param {
lr_mult:
}
}
##############
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size:
stride:
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
convolution_param {
num_output:
pad:
stride:
kernel_size:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
##############
layer {
bottom: "conv3"
top: "conv3"
name: "bn3"
type: "BatchNorm"
param {
lr_mult:
}
param {
lr_mult:
}
param {
lr_mult:
}
}
##############
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
convolution_param {
num_output:
pad:
kernel_size:
group:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
##############
layer {
bottom: "conv4"
top: "conv4"
name: "bn4"
type: "BatchNorm"
param {
lr_mult:
}
param {
lr_mult:
}
param {
lr_mult:
}
}
##############
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
convolution_param {
num_output:
pad:
stride:
kernel_size:
group:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
##############
layer {
bottom: "conv5"
top: "conv5"
name: "bn5"
type: "BatchNorm"
param {
lr_mult:
}
param {
lr_mult:
}
param {
lr_mult:
}
}
##############
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size:
stride:
}
}
layer {
name: "fc6_srx"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
inner_product_param {
num_output:
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value:
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7_srx"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param {
lr_mult:
decay_mult:
}
param {
lr_mult:
decay_mult:
}
inner_product_param {
num_output:
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value:
}
}
}
layer{
name: "loss"
type: "SoftmaxWithLoss"
top: "SoftmaxWithLoss"
bottom: "fc7"
bottom: "label"
include {
phase: TRAIN
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc7"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}