NLN中的MLP操作

MLP操作：


# 前面是正常的卷积操作
# 这里是mlp conv, 可以看出就是一个1*1的卷积操作(等价于全连接操作)
layers {
bottom: "conv1"
top: "cccp1"
name: "cccp1"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 96
kernel_size: 1
stride: 1
weight_filler {
type: "gaussian"
mean: 0
std: 0.05
}
bias_filler {
type: "constant"
value: 0
}
}
}
# 接着接一个激活函数
layers {
bottom: "cccp1"
top: "cccp1"
name: "relu1"
type: RELU
}
# 在来一个用1*1的卷积完成的全连接操作
layers {
bottom: "cccp1"
top: "cccp2"
name: "cccp2"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 96
kernel_size: 1
stride: 1
weight_filler {
type: "gaussian"
mean: 0
std: 0.05
}
bias_filler {
type: "constant"
value: 0
}
}
}
# 接对应的激活函数
layers {
bottom: "cccp2"
top: "cccp2"
name: "relu2"
type: RELU
}
# 以上完成了两次非线性映射, 也就是 MLP 操作
layers {
bottom: "cccp2"
top: "pool0"
name: "pool0"
type: POOLING
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layers {
bottom: "pool0"
top: "conv2"
name: "conv2"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
stride: 1
weight_filler {
type: "gaussian"
mean: 0
std: 0.05
}
bias_filler {
type: "constant"
value: 0
}
}
}

也是解决overfitting的一种方法