以如下的一個網絡為例：
name: "vgg19"
layer {
name: "data"
type: "Input"
top: "data"
input_param {
shape {
dim: 1
dim: 3
dim: 224
dim: 224
}
}
}
layer {
bottom: "data"
top: "conv1_1"
name: "conv1_1"
type: "Convolution"
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv1_1"
top: "conv1_1"
name: "relu1_1"
type: "ReLU"
}
layer {
bottom: "conv1_1"
top: "conv1_2"
name: "conv1_2"
type: "Convolution"
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv1_2"
top: "conv1_2"
name: "relu1_2"
type: "ReLU"
}
layer {
bottom: "conv1_2"
top: "pool1"
name: "pool1"
type: "Pooling"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
bottom: "pool1"
top: "conv2_1"
name: "conv2_1"
type: "Convolution"
convolution_param {
num_output: 128
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv2_1"
top: "conv2_1"
name: "relu2_1"
type: "ReLU"
}
layer {
bottom: "conv2_1"
top: "conv2_2"
name: "conv2_2"
type: "Convolution"
convolution_param {
num_output: 128
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv2_2"
top: "conv2_2"
name: "relu2_2"
type: "ReLU"
}
layer {
bottom: "conv2_2"
top: "pool2"
name: "pool2"
type: "Pooling"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
bottom: "pool2"
top: "conv3_1"
name: "conv3_1"
type: "Convolution"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv3_1"
top: "conv3_1"
name: "relu3_1"
type: "ReLU"
}
layer {
bottom: "conv3_1"
top: "conv3_2"
name: "conv3_2"
type: "Convolution"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv3_2"
top: "conv3_2"
name: "relu3_2"
type: "ReLU"
}
layer {
bottom: "conv3_2"
top: "conv3_3"
name: "conv3_3"
type: "Convolution"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv3_3"
top: "conv3_3"
name: "relu3_3"
type: "ReLU"
}
layer {
bottom: "conv3_3"
top: "conv3_4"
name: "conv3_4"
type: "Convolution"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv3_4"
top: "conv3_4"
name: "relu3_4"
type: "ReLU"
}
layer {
bottom: "conv3_4"
top: "pool3"
name: "pool3"
type: "Pooling"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
bottom: "pool3"
top: "conv4_1"
name: "conv4_1"
type: "Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv4_1"
top: "conv4_1"
name: "relu4_1"
type: "ReLU"
}
layer {
bottom: "conv4_1"
top: "conv4_2"
name: "conv4_2"
type: "Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv4_2"
top: "conv4_2"
name: "relu4_2"
type: "ReLU"
}
layer {
bottom: "conv4_2"
top: "conv4_3"
name: "conv4_3"
type: "Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv4_3"
top: "conv4_3"
name: "relu4_3"
type: "ReLU"
}
layer {
bottom: "conv4_3"
top: "conv4_4"
name: "conv4_4"
type: "Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv4_4"
top: "conv4_4"
name: "relu4_4"
type: "ReLU"
}
layer {
bottom: "conv4_4"
top: "pool4"
name: "pool4"
type: "Pooling"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
bottom: "pool4"
top: "conv5_1"
name: "conv5_1"
type: "Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv5_1"
top: "conv5_1"
name: "relu5_1"
type: "ReLU"
}
layer {
bottom: "conv5_1"
top: "conv5_2"
name: "conv5_2"
type: "Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv5_2"
top: "conv5_2"
name: "relu5_2"
type: "ReLU"
}
layer {
bottom: "conv5_2"
top: "conv5_3"
name: "conv5_3"
type: "Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv5_3"
top: "conv5_3"
name: "relu5_3"
type: "ReLU"
}
layer {
bottom: "conv5_3"
top: "conv5_4"
name: "conv5_4"
type: "Convolution"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
bottom: "conv5_4"
top: "conv5_4"
name: "relu5_4"
type: "ReLU"
}
layer {
bottom: "conv5_4"
top: "pool5"
name: "pool5"
type: "Pooling"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
bottom: "pool5"
top: "fc6"
name: "fc6"
type: "InnerProduct"
inner_product_param {
num_output: 4096
}
}
layer {
bottom: "fc6"
top: "fc6"
name: "relu6"
type: "ReLU"
}
layer {
bottom: "fc6"
top: "fc6"
name: "drop6"
type: "Dropout"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
bottom: "fc6"
top: "fc7"
name: "fc7"
type: "InnerProduct"
inner_product_param {
num_output: 4096
}
}
layer {
bottom: "fc7"
top: "fc7"
name: "relu7"
type: "ReLU"
}
layer {
bottom: "fc7"
top: "fc7"
name: "drop7"
type: "Dropout"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
bottom: "fc7"
top: "fc8"
name: "fc8"
type: "InnerProduct"
inner_product_param {
num_output: 1000
}
}
layer {
bottom: "fc8"
top: "prob"
name: "prob"
type: "Softmax"
}
圖形化如下：
每一層的計算量包括：
MACC= [卷積核的長*寬] * [輸出(目標)層的長*寬] * 輸入的channel * 輸出的channel
Compare = [輸出(目標)層的長*寬] * 輸入的channel
存儲空間：圖形的大小， [輸出(目標)層的長*寬] * 輸入的channel
參數空間：是存儲空間的5倍左右，:
第一層：3*3*3*64 +64 = 1792
3(卷積核寬)*3(卷積核高)*3(卷積核通道數)*64(64組卷積核) +64(卷積核偏移量)
第二層：3*3*64*64 + 64 = 36928
3(卷積核寬)*3(卷積核高)*64(卷積核通道數或者叫做深度)*64(64組卷積核) +64(卷積核偏移量)
第四層：3 * 3 * 64 * 128 + 128 = 7385
這樣一個模型運行一遍需要的算力約：
這對CPU這類串行運算，還是很考驗的。同時，大量的參數和圖形數據的交互。