一、介紹
ResNet系列網絡,圖像分類領域的知名算法,經久不衰,歷久彌新,直到今天依舊具有廣泛的研究意義和應用場景。被業界各種改進,經常用於圖像識別任務。
今天主要介紹一下ResNet-18網絡結構,其他深層次網絡,可以依次類推。
ResNet-18,數字代表的是網絡的深度,也就是說ResNet18 網絡就是18層的嗎?實則不然,其實這裏的18指定的是帶有權重的 18層,包括卷積層和全連接層,不包括池化層和BN層。
二、網絡結構
本文主要基於caffe框架,解讀Resnet-18網絡結構~
1. 網絡參數
2. 網絡圖示
網絡結構圖,由caffe train.prototxt文件內容繪製:
caffe train.prototxt文件內容:
name: "ResNet-18"
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 224
mean_file: "/home/vgenty/git/caffe/build/tools/ub_seven_class_train_mean.binary"
}
data_param {
source: "/home/vgenty/git/caffe/build/tools/ub_seven_class_train.db"
batch_size: 8
backend: LMDB
}
}
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mirror: false
crop_size: 224
mean_file: "/home/vgenty/git/caffe/build/tools/ub_seven_class_valid_mean.binary"
}
data_param {
source: "/home/vgenty/git/caffe/build/tools/ub_seven_class_valid.db"
batch_size:8
backend: LMDB
}
}
layer {
bottom: "data"
top: "conv1"
name: "conv1"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 7
pad: 3
stride: 2
}
}
layer {
bottom: "conv1"
top: "conv1"
name: "bn_conv1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "conv1"
top: "conv1"
name: "scale_conv1"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "conv1"
top: "conv1"
name: "conv1_relu"
type: "ReLU"
}
layer {
bottom: "conv1"
top: "pool1"
name: "pool1"
type: "Pooling"
pooling_param {
kernel_size: 3
stride: 2
pool: MAX
}
}
##########################
######first shortcut######
##########################
layer {
bottom: "pool1"
top: "res2a_branch1"
name: "res2a_branch1"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 1
pad: 0
stride: 1
bias_term: false
}
}
layer {
bottom: "res2a_branch1"
top: "res2a_branch1"
name: "bn2a_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res2a_branch1"
top: "res2a_branch1"
name: "scale2a_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "pool1"
top: "res2a_branch2a"
name: "res2a_branch2a"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res2a_branch2a"
top: "res2a_branch2a"
name: "bn2a_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res2a_branch2a"
top: "res2a_branch2a"
name: "scale2a_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res2a_branch2a"
top: "res2a_branch2a"
name: "res2a_branch2a_relu"
type: "ReLU"
}
layer {
bottom: "res2a_branch2a"
top: "res2a_branch2b"
name: "res2a_branch2b"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res2a_branch2b"
top: "res2a_branch2b"
name: "bn2a_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res2a_branch2b"
top: "res2a_branch2b"
name: "scale2a_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res2a_branch1"
bottom: "res2a_branch2b"
top: "res2a"
name: "res2a"
type: "Eltwise"
}
layer {
bottom: "res2a"
top: "res2a"
name: "res2a_relu"
type: "ReLU"
}
##########################
######first-2 shortcut####
##########################
layer {
bottom: "res2a"
top: "res2b_branch1"
name: "res2b_branch1"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 1
pad: 0
stride: 1
bias_term: false
}
}
layer {
bottom: "res2b_branch1"
top: "res2b_branch1"
name: "bn2b_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res2b_branch1"
top: "res2b_branch1"
name: "scale2b_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res2a"
top: "res2b_branch2a"
name: "res2b_branch2a"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res2b_branch2a"
top: "res2b_branch2a"
name: "bn2b_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res2b_branch2a"
top: "res2b_branch2a"
name: "scale2b_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res2b_branch2a"
top: "res2b_branch2a"
name: "res2b_branch2a_relu"
type: "ReLU"
}
layer {
bottom: "res2b_branch2a"
top: "res2b_branch2b"
name: "res2b_branch2b"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res2b_branch2b"
top: "res2b_branch2b"
name: "bn2b_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res2b_branch2b"
top: "res2b_branch2b"
name: "scale2b_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res2b_branch1"
bottom: "res2b_branch2b"
top: "res2b"
name: "res2b"
type: "Eltwise"
}
layer {
bottom: "res2b"
top: "res2b"
name: "res2b_relu"
type: "ReLU"
}
##########################
######second shortcut#####
##########################
layer {
bottom: "res2b"
top: "res3a_branch1"
name: "res3a_branch1"
type: "Convolution"
convolution_param {
num_output: 128
kernel_size: 1
pad: 0
stride: 2
bias_term: false
}
}
layer {
bottom: "res3a_branch1"
top: "res3a_branch1"
name: "bn3a_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res3a_branch1"
top: "res3a_branch1"
name: "scale3a_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res2b"
top: "res3a_branch2a"
name: "res3a_branch2a"
type: "Convolution"
convolution_param {
num_output: 128
kernel_size: 3
pad: 1
stride: 2
bias_term: false
}
}
layer {
bottom: "res3a_branch2a"
top: "res3a_branch2a"
name: "bn3a_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res3a_branch2a"
top: "res3a_branch2a"
name: "scale3a_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res3a_branch2a"
top: "res3a_branch2a"
name: "res3a_branch2a_relu"
type: "ReLU"
}
layer {
bottom: "res3a_branch2a"
top: "res3a_branch2b"
name: "res3a_branch2b"
type: "Convolution"
convolution_param {
num_output: 128
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res3a_branch2b"
top: "res3a_branch2b"
name: "bn3a_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res3a_branch2b"
top: "res3a_branch2b"
name: "scale3a_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res3a_branch1"
bottom: "res3a_branch2b"
top: "res3a"
name: "res3a"
type: "Eltwise"
}
layer {
bottom: "res3a"
top: "res3a"
name: "res3a_relu"
type: "ReLU"
}
##########################
######second-2 shortcut#####
##########################
layer {
bottom: "res3a"
top: "res3b_branch1"
name: "res3b_branch1"
type: "Convolution"
convolution_param {
num_output: 128
kernel_size: 1
pad: 0
stride: 1
bias_term: false
}
}
layer {
bottom: "res3b_branch1"
top: "res3b_branch1"
name: "bn3b_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res3b_branch1"
top: "res3b_branch1"
name: "scale3b_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res3a"
top: "res3b_branch2a"
name: "res3b_branch2a"
type: "Convolution"
convolution_param {
num_output: 128
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res3b_branch2a"
top: "res3b_branch2a"
name: "bn3b_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res3b_branch2a"
top: "res3b_branch2a"
name: "scale3b_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res3b_branch2a"
top: "res3b_branch2a"
name: "res3b_branch2a_relu"
type: "ReLU"
}
layer {
bottom: "res3b_branch2a"
top: "res3b_branch2b"
name: "res3b_branch2b"
type: "Convolution"
convolution_param {
num_output: 128
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res3b_branch2b"
top: "res3b_branch2b"
name: "bn3b_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res3b_branch2b"
top: "res3b_branch2b"
name: "scale3b_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res3b_branch1"
bottom: "res3b_branch2b"
top: "res3b"
name: "res3b"
type: "Eltwise"
}
layer {
bottom: "res3b"
top: "res3b"
name: "res3b_relu"
type: "ReLU"
}
##########################
######third shortcut#####
##########################
layer {
bottom: "res3b"
top: "res4a_branch1"
name: "res4a_branch1"
type: "Convolution"
convolution_param {
num_output: 256
kernel_size: 1
pad: 0
stride: 2
bias_term: false
}
}
layer {
bottom: "res4a_branch1"
top: "res4a_branch1"
name: "bn4a_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res4a_branch1"
top: "res4a_branch1"
name: "scale4a_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res3b"
top: "res4a_branch2a"
name: "res4a_branch2a"
type: "Convolution"
convolution_param {
num_output: 256
kernel_size: 3
pad: 1
stride: 2
bias_term: false
}
}
layer {
bottom: "res4a_branch2a"
top: "res4a_branch2a"
name: "bn4a_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res4a_branch2a"
top: "res4a_branch2a"
name: "scale4a_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res4a_branch2a"
top: "res4a_branch2a"
name: "res4a_branch2a_relu"
type: "ReLU"
}
layer {
bottom: "res4a_branch2a"
top: "res4a_branch2b"
name: "res4a_branch2b"
type: "Convolution"
convolution_param {
num_output: 256
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res4a_branch2b"
top: "res4a_branch2b"
name: "bn4a_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res4a_branch2b"
top: "res4a_branch2b"
name: "scale4a_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res4a_branch1"
bottom: "res4a_branch2b"
top: "res4a"
name: "res4a"
type: "Eltwise"
}
layer {
bottom: "res4a"
top: "res4a"
name: "res4a_relu"
type: "ReLU"
}
###########################
######third-2 shortcut#####
##########################
layer {
bottom: "res4a"
top: "res4b_branch1"
name: "res4b_branch1"
type: "Convolution"
convolution_param {
num_output: 256
kernel_size: 1
pad: 0
stride: 1
bias_term: false
}
}
layer {
bottom: "res4b_branch1"
top: "res4b_branch1"
name: "bn4b_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res4b_branch1"
top: "res4b_branch1"
name: "scale4b_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res4a"
top: "res4b_branch2a"
name: "res4b_branch2a"
type: "Convolution"
convolution_param {
num_output: 256
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res4b_branch2a"
top: "res4b_branch2a"
name: "bn4b_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res4b_branch2a"
top: "res4b_branch2a"
name: "scale4b_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res4b_branch2a"
top: "res4b_branch2a"
name: "res4b_branch2a_relu"
type: "ReLU"
}
layer {
bottom: "res4b_branch2a"
top: "res4b_branch2b"
name: "res4b_branch2b"
type: "Convolution"
convolution_param {
num_output: 256
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res4b_branch2b"
top: "res4b_branch2b"
name: "bn4b_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res4b_branch2b"
top: "res4b_branch2b"
name: "scale4b_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res4b_branch1"
bottom: "res4b_branch2b"
top: "res4b"
name: "res4b"
type: "Eltwise"
}
layer {
bottom: "res4b"
top: "res4b"
name: "res4b_relu"
type: "ReLU"
}
##########################
######forth shortcut#####
##########################
layer {
bottom: "res4b"
top: "res5a_branch1"
name: "res5a_branch1"
type: "Convolution"
convolution_param {
num_output: 512
kernel_size: 1
pad: 0
stride: 2
bias_term: false
}
}
layer {
bottom: "res5a_branch1"
top: "res5a_branch1"
name: "bn5a_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res5a_branch1"
top: "res5a_branch1"
name: "scale5a_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res4b"
top: "res5a_branch2a"
name: "res5a_branch2a"
type: "Convolution"
convolution_param {
num_output: 512
kernel_size: 3
pad: 1
stride: 2
bias_term: false
}
}
layer {
bottom: "res5a_branch2a"
top: "res5a_branch2a"
name: "bn5a_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res5a_branch2a"
top: "res5a_branch2a"
name: "scale5a_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res5a_branch2a"
top: "res5a_branch2a"
name: "res5a_branch2a_relu"
type: "ReLU"
}
layer {
bottom: "res5a_branch2a"
top: "res5a_branch2b"
name: "res5a_branch2b"
type: "Convolution"
convolution_param {
num_output: 512
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res5a_branch2b"
top: "res5a_branch2b"
name: "bn5a_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res5a_branch2b"
top: "res5a_branch2b"
name: "scale5a_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res5a_branch1"
bottom: "res5a_branch2b"
top: "res5a"
name: "res5a"
type: "Eltwise"
}
layer {
bottom: "res5a"
top: "res5a"
name: "res5a_relu"
type: "ReLU"
}
##########################
######forth-2 shortcut#####
##########################
layer {
bottom: "res5a"
top: "res5b_branch1"
name: "res5b_branch1"
type: "Convolution"
convolution_param {
num_output: 512
kernel_size: 1
pad: 0
stride: 1
bias_term: false
}
}
layer {
bottom: "res5b_branch1"
top: "res5b_branch1"
name: "bn5b_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res5b_branch1"
top: "res5b_branch1"
name: "scale5b_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res5a"
top: "res5b_branch2a"
name: "res5b_branch2a"
type: "Convolution"
convolution_param {
num_output: 512
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res5b_branch2a"
top: "res5b_branch2a"
name: "bn5b_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res5b_branch2a"
top: "res5b_branch2a"
name: "scale5b_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res5b_branch2a"
top: "res5b_branch2a"
name: "res5b_branch2a_relu"
type: "ReLU"
}
layer {
bottom: "res5b_branch2a"
top: "res5b_branch2b"
name: "res5b_branch2b"
type: "Convolution"
convolution_param {
num_output: 512
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}
layer {
bottom: "res5b_branch2b"
top: "res5b_branch2b"
name: "bn5b_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}
layer {
bottom: "res5b_branch2b"
top: "res5b_branch2b"
name: "scale5b_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}
layer {
bottom: "res5b_branch1"
bottom: "res5b_branch2b"
top: "res5b"
name: "res5b"
type: "Eltwise"
}
layer {
bottom: "res5b"
top: "res5b"
name: "res5b_relu"
type: "ReLU"
}
layer {
bottom: "res5b"
top: "pool5"
name: "pool5"
type: "Pooling"
pooling_param {
kernel_size: 7
stride: 1
pool: AVE
}
}
layer {
bottom: "pool5"
top: "fc7"
name: "fc7"
type: "InnerProduct"
inner_product_param {
num_output: 7
}
}
#layer {
# bottom: "fc7"
# top: "prob"
# name: "prob"
# type: "Softmax"
# }
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc7"
bottom: "label"
top: "loss"
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc7"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
詳細參數設置,可查看以上文件內容定義。
三、總結
ResNet及其變體網路系列,對於一般的圖像識別任務表現優異,具體場景的算法應用,可以結合實際情況,進行具體網絡結構改進,如網路裁剪,網絡加深或其它策略,可以進行實踐改進。
碼字不易,如有不對,歡迎留言交流~
您的支持,是我不斷創作的最大動力~
歡迎點贊,關注,留言交流~
深度學習,樂此不疲~
個人微信公衆號,歡迎關注~