1、Cirf10_quick
学习率改变的迭代数 4000(0.001) 5000(0.0001)
网络中没有 归一化层
全连接有两层:
layer {name: "ip1"type: "InnerProduct"bottom: "pool3"top: "ip1"param {lr_mult: 1}param {lr_mult: 2}inner_product_param {num_output: 64}}layer {name: "ip2"type: "InnerProduct"bottom: "ip1"top: "ip2"param {lr_mult: 1}param {lr_mult: 2}inner_product_param {num_output: 10}}
2、 Cirf10_full
学习率改变的迭代数 6000(0.001) 6500(0.0001) 7000(0.00001)
网络中有 norm1 / norm2 归一化层 :
layer {
name: "norm1"
type: "LRN"
bottom: "pool1"
top: "norm1"
lrn_param {
local_size: 3
alpha: 5e-05
beta: 0.75
norm_region: WITHIN_CHANNEL
}
}
全连接只有一层(慢):
layer {
name: "ip1"
type: "InnerProduct"
bottom: "pool3"
top: "ip1"
param {
lr_mult: 1
decay_mult: 250
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 10
}
}