国产 无码 综合区,色欲AV无码国产永久播放,无码天堂亚洲国产AV,国产日韩欧美女同一区二区

  1. Toy模板網(wǎng)首頁(yè)
  2. >Toy博客

ResNet代碼復(fù)現(xiàn)＋超詳細(xì)注釋（PyTorch）

2年前作者：路人賈'ω'分類：Toy博客閱讀(28)違法舉報(bào)

這篇具有很好參考價(jià)值的文章主要介紹了ResNet代碼復(fù)現(xiàn)＋超詳細(xì)注釋（PyTorch）。希望對(duì)大家有所幫助。如果存在錯(cuò)誤或未考慮完全的地方，請(qǐng)大家不吝賜教，您也可以點(diǎn)擊"舉報(bào)違法"按鈕提交疑問。

關(guān)于ResNet的原理和具體細(xì)節(jié)，可參見上篇解讀：經(jīng)典神經(jīng)網(wǎng)絡(luò)論文超詳細(xì)解讀（五）——ResNet（殘差網(wǎng)絡(luò)）學(xué)習(xí)筆記（翻譯＋精讀＋代碼復(fù)現(xiàn)）

接下來我們就來復(fù)現(xiàn)一下代碼。

源代碼比較復(fù)雜，感興趣的同學(xué)可以上官網(wǎng)學(xué)習(xí)：?

https://github.com/pytorch/vision/tree/master/torchvision

本篇是簡(jiǎn)化版本?

?一、BasicBlock模塊

BasicBlock結(jié)構(gòu)圖如圖所示：

ResNet代碼復(fù)現(xiàn)＋超詳細(xì)注釋（PyTorch）

?BasicBlock是基礎(chǔ)版本，主要用來構(gòu)建ResNet18和ResNet34網(wǎng)絡(luò)，里面只包含兩個(gè)卷積層，使用了兩個(gè) 3*3 的卷積，通道數(shù)都是64，卷積后接著 BN 和 ReLU。

右邊的曲線就是Shortcut Connections，將輸入x加到輸出。

代碼：

'''-------------一、BasicBlock模塊-----------------------------'''
# 用于ResNet18和ResNet34基本殘差結(jié)構(gòu)塊
class BasicBlock(nn.Module):
    def __init__(self, inchannel, outchannel, stride=1):
        super(BasicBlock, self).__init__()
        self.left = nn.Sequential(
            nn.Conv2d(inchannel, outchannel, kernel_size=3, stride=stride, padding=1, bias=False),
            nn.BatchNorm2d(outchannel),
            nn.ReLU(inplace=True), #inplace=True表示進(jìn)行原地操作，一般默認(rèn)為False，表示新建一個(gè)變量存儲(chǔ)操作
            nn.Conv2d(outchannel, outchannel, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(outchannel)
        )
        self.shortcut = nn.Sequential()
        #論文中模型架構(gòu)的虛線部分，需要下采樣
        if stride != 1 or inchannel != outchannel:
            self.shortcut = nn.Sequential(
                nn.Conv2d(inchannel, outchannel, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(outchannel)
            )

    def forward(self, x):
        out = self.left(x) #這是由于殘差塊需要保留原始輸入
        out += self.shortcut(x)#這是ResNet的核心，在輸出上疊加了輸入x
        out = F.relu(out)
        return out

二、Bottleneck 模塊

Bottleneck結(jié)構(gòu)圖如圖所示：

ResNet代碼復(fù)現(xiàn)＋超詳細(xì)注釋（PyTorch）

Bottleneck主要用在ResNet50及以上的網(wǎng)絡(luò)結(jié)構(gòu)，與BasicBlock不同的是這里有 3 個(gè)卷積，分別為 1*1，3*3，1*1大小的卷積核，分別用于壓縮維度、卷積處理、恢復(fù)維度。
這里的通道數(shù)是變化的，1*1卷積層的作用就是用于改變特征圖的通數(shù)，使得可以和恒等映射x相疊加，另外這里的1*1卷積層改變維度的很重要的一點(diǎn)是可以降低網(wǎng)絡(luò)參數(shù)量，這也是為什么更深層的網(wǎng)絡(luò)采用BottleNeck而不是BasicBlock的原因。

注意：這里outchannel / 4是因?yàn)锽ottleneck層輸出通道都是輸入的4倍

代碼：

'''-------------二、Bottleneck模塊-----------------------------'''
# 用于ResNet50及以上的殘差結(jié)構(gòu)塊
class Bottleneck(nn.Module):
    def __init__(self, inchannel, outchannel, stride=1):
        super(Bottleneck, self).__init__()
        self.left = nn.Sequential(
            nn.Conv2d(inchannel, int(outchannel / 4), kernel_size=1, stride=stride, padding=0, bias=False),
            nn.BatchNorm2d(int(outchannel / 4)),
            nn.ReLU(inplace=True),
            nn.Conv2d(int(outchannel / 4), int(outchannel / 4), kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(int(outchannel / 4)),
            nn.ReLU(inplace=True),
            nn.Conv2d(int(outchannel / 4), outchannel, kernel_size=1, stride=1, padding=0, bias=False),
            nn.BatchNorm2d(outchannel),
        )
        self.shortcut = nn.Sequential()
        if stride != 1 or inchannel != outchannel:
            self.shortcut = nn.Sequential(
                nn.Conv2d(inchannel, outchannel, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(outchannel)
            )

    def forward(self, x):
        out = self.left(x)
        y = self.shortcut(x)
        out += self.shortcut(x)
        out = F.relu(out)
        return out

三、ResNet主體

介紹了上述BasicBlock基礎(chǔ)塊和BotteNeck結(jié)構(gòu)后，我們就可以搭建ResNet結(jié)構(gòu)了。

5種不同層數(shù)的ResNet結(jié)構(gòu)圖如圖所示：

ResNet代碼復(fù)現(xiàn)＋超詳細(xì)注釋（PyTorch）

代碼：?

ResNet18

'''----------ResNet18----------'''
class ResNet_18(nn.Module):
    def __init__(self, ResidualBlock, num_classes=10):
        super(ResNet_18, self).__init__()
        self.inchannel = 64
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(),
        )
        self.layer1 = self.make_layer(ResidualBlock, 64, 2, stride=1)
        self.layer2 = self.make_layer(ResidualBlock, 128, 2, stride=2)
        self.layer3 = self.make_layer(ResidualBlock, 256, 2, stride=2)
        self.layer4 = self.make_layer(ResidualBlock, 512, 2, stride=2)
        self.fc = nn.Linear(512, num_classes)

    def make_layer(self, block, channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)  # strides=[1,1]
        layers = []
        for stride in strides:
            layers.append(block(self.inchannel, channels, stride))
            self.inchannel = channels
        return nn.Sequential(*layers)

    def forward(self, x):  # 3*32*32
        out = self.conv1(x)  # 64*32*32
        out = self.layer1(out)  # 64*32*32
        out = self.layer2(out)  # 128*16*16
        out = self.layer3(out)  # 256*8*8
        out = self.layer4(out)  # 512*4*4
        out = F.avg_pool2d(out, 4)  # 512*1*1
        out = out.view(out.size(0), -1)  # 512
        out = self.fc(out)
        return out

ResNet34

'''----------ResNet34----------'''
class ResNet_34(nn.Module):
    def __init__(self, ResidualBlock, num_classes=10):
        super(ResNet_34, self).__init__()
        self.inchannel = 64
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(),
        )
        self.layer1 = self.make_layer(ResidualBlock, 64, 3, stride=1)
        self.layer2 = self.make_layer(ResidualBlock, 128, 4, stride=2)
        self.layer3 = self.make_layer(ResidualBlock, 256, 6, stride=2)
        self.layer4 = self.make_layer(ResidualBlock, 512, 3, stride=2)
        self.fc = nn.Linear(512, num_classes)

    def make_layer(self, block, channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)  # strides=[1,1]
        layers = []
        for stride in strides:
            layers.append(block(self.inchannel, channels, stride))
            self.inchannel = channels
        return nn.Sequential(*layers)

    def forward(self, x):  # 3*32*32
        out = self.conv1(x)  # 64*32*32
        out = self.layer1(out)  # 64*32*32
        out = self.layer2(out)  # 128*16*16
        out = self.layer3(out)  # 256*8*8
        out = self.layer4(out)  # 512*4*4
        out = F.avg_pool2d(out, 4)  # 512*1*1
        out = out.view(out.size(0), -1)  # 512
        out = self.fc(out)
        return out

ResNet50

'''---------ResNet50--------'''
class ResNet_50(nn.Module):
    def __init__(self, ResidualBlock, num_classes=10):
        super(ResNet_50, self).__init__()
        self.inchannel = 64
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(),
        )
        self.layer1 = self.make_layer(ResidualBlock, 256, 3, stride=1)
        self.layer2 = self.make_layer(ResidualBlock, 512, 4, stride=2)
        self.layer3 = self.make_layer(ResidualBlock, 1024, 6, stride=2)
        self.layer4 = self.make_layer(ResidualBlock, 2048, 3, stride=2)
        self.fc = nn.Linear(512 * 4, num_classes)
        # **************************

    def make_layer(self, block, channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)  # strides=[1,1]
        layers = []
        for stride in strides:
            layers.append(block(self.inchannel, channels, stride))
            self.inchannel = channels
        return nn.Sequential(*layers)

    def forward(self, x):  # 3*32*32
        out = self.conv1(x)  # 64*32*32
        out = self.layer1(out)  # 64*32*32
        out = self.layer2(out)  # 128*16*16
        out = self.layer3(out)  # 256*8*8
        out = self.layer4(out)  # 512*4*4
        out = F.avg_pool2d(out, 4)  # 512*1*1
        # print(out.size())
        out = out.view(out.size(0), -1)  # 512
        out = self.fc(out)
        return out

四、完整代碼

import torch
import torch.nn as nn
import torch.nn.functional as F


'''-------------一、BasicBlock模塊-----------------------------'''
# 用于ResNet18和ResNet34基本殘差結(jié)構(gòu)塊
class BasicBlock(nn.Module):
    def __init__(self, inchannel, outchannel, stride=1):
        super(BasicBlock, self).__init__()
        self.left = nn.Sequential(
            nn.Conv2d(inchannel, outchannel, kernel_size=3, stride=stride, padding=1, bias=False),
            nn.BatchNorm2d(outchannel),
            nn.ReLU(inplace=True), #inplace=True表示進(jìn)行原地操作，一般默認(rèn)為False，表示新建一個(gè)變量存儲(chǔ)操作
            nn.Conv2d(outchannel, outchannel, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(outchannel)
        )
        self.shortcut = nn.Sequential()
        #論文中模型架構(gòu)的虛線部分，需要下采樣
        if stride != 1 or inchannel != outchannel:
            self.shortcut = nn.Sequential(
                nn.Conv2d(inchannel, outchannel, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(outchannel)
            )

    def forward(self, x):
        out = self.left(x) #這是由于殘差塊需要保留原始輸入
        out += self.shortcut(x)#這是ResNet的核心，在輸出上疊加了輸入x
        out = F.relu(out)
        return out


'''-------------二、Bottleneck模塊-----------------------------'''
# 用于ResNet50及以上的殘差結(jié)構(gòu)塊
class Bottleneck(nn.Module):
    def __init__(self, inchannel, outchannel, stride=1):
        super(Bottleneck, self).__init__()
        self.left = nn.Sequential(
            nn.Conv2d(inchannel, int(outchannel / 4), kernel_size=1, stride=stride, padding=0, bias=False),
            nn.BatchNorm2d(int(outchannel / 4)),
            nn.ReLU(inplace=True),
            nn.Conv2d(int(outchannel / 4), int(outchannel / 4), kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(int(outchannel / 4)),
            nn.ReLU(inplace=True),
            nn.Conv2d(int(outchannel / 4), outchannel, kernel_size=1, stride=1, padding=0, bias=False),
            nn.BatchNorm2d(outchannel),
        )
        self.shortcut = nn.Sequential()
        if stride != 1 or inchannel != outchannel:
            self.shortcut = nn.Sequential(
                nn.Conv2d(inchannel, outchannel, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(outchannel)
            )

    def forward(self, x):
        out = self.left(x)
        y = self.shortcut(x)
        out += self.shortcut(x)
        out = F.relu(out)
        return out

'''-------------ResNet18---------------'''
class ResNet_18(nn.Module):
    def __init__(self, ResidualBlock, num_classes=10):
        super(ResNet_18, self).__init__()
        self.inchannel = 64
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(),
        )
        self.layer1 = self.make_layer(ResidualBlock, 64, 2, stride=1)
        self.layer2 = self.make_layer(ResidualBlock, 128, 2, stride=2)
        self.layer3 = self.make_layer(ResidualBlock, 256, 2, stride=2)
        self.layer4 = self.make_layer(ResidualBlock, 512, 2, stride=2)
        self.fc = nn.Linear(512, num_classes)

    def make_layer(self, block, channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)  # strides=[1,1]
        layers = []
        for stride in strides:
            layers.append(block(self.inchannel, channels, stride))
            self.inchannel = channels
        return nn.Sequential(*layers)

    def forward(self, x):  # 3*32*32
        out = self.conv1(x)  # 64*32*32
        out = self.layer1(out)  # 64*32*32
        out = self.layer2(out)  # 128*16*16
        out = self.layer3(out)  # 256*8*8
        out = self.layer4(out)  # 512*4*4
        out = F.avg_pool2d(out, 4)  # 512*1*1
        out = out.view(out.size(0), -1)  # 512
        out = self.fc(out)
        return out

'''-------------ResNet34---------------'''
class ResNet_34(nn.Module):
    def __init__(self, ResidualBlock, num_classes=10):
        super(ResNet_34, self).__init__()
        self.inchannel = 64
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(),
        )
        self.layer1 = self.make_layer(ResidualBlock, 64, 3, stride=1)
        self.layer2 = self.make_layer(ResidualBlock, 128, 4, stride=2)
        self.layer3 = self.make_layer(ResidualBlock, 256, 6, stride=2)
        self.layer4 = self.make_layer(ResidualBlock, 512, 3, stride=2)
        self.fc = nn.Linear(512, num_classes)

    def make_layer(self, block, channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)  # strides=[1,1]
        layers = []
        for stride in strides:
            layers.append(block(self.inchannel, channels, stride))
            self.inchannel = channels
        return nn.Sequential(*layers)

    def forward(self, x):  # 3*32*32
        out = self.conv1(x)  # 64*32*32
        out = self.layer1(out)  # 64*32*32
        out = self.layer2(out)  # 128*16*16
        out = self.layer3(out)  # 256*8*8
        out = self.layer4(out)  # 512*4*4
        out = F.avg_pool2d(out, 4)  # 512*1*1
        out = out.view(out.size(0), -1)  # 512
        out = self.fc(out)
        return out

'''-------------ResNet50---------------'''
class ResNet_50(nn.Module):
    def __init__(self, ResidualBlock, num_classes=10):
        super(ResNet_50, self).__init__()
        self.inchannel = 64
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(),
        )
        self.layer1 = self.make_layer(ResidualBlock, 256, 3, stride=1)
        self.layer2 = self.make_layer(ResidualBlock, 512, 4, stride=2)
        self.layer3 = self.make_layer(ResidualBlock, 1024, 6, stride=2)
        self.layer4 = self.make_layer(ResidualBlock, 2048, 3, stride=2)
        self.fc = nn.Linear(512 * 4, num_classes)
        # **************************

    def make_layer(self, block, channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)  # strides=[1,1]
        layers = []
        for stride in strides:
            layers.append(block(self.inchannel, channels, stride))
            self.inchannel = channels
        return nn.Sequential(*layers)

    def forward(self, x):  # 3*32*32
        out = self.conv1(x)  # 64*32*32
        out = self.layer1(out)  # 64*32*32
        out = self.layer2(out)  # 128*16*16
        out = self.layer3(out)  # 256*8*8
        out = self.layer4(out)  # 512*4*4
        out = F.avg_pool2d(out, 4)  # 512*1*1
        # print(out.size())
        out = out.view(out.size(0), -1)  # 512
        out = self.fc(out)
        return out


def ResNet18():
    return ResNet_18(BasicBlock)


def ResNet34():
    return ResNet_34(BasicBlock)


def ResNet50():
    return ResNet_50(Bottleneck)

本篇到這里就結(jié)束啦，有什么問題，歡迎大家留言討論~文章來源地址http://www.zghlxwxcb.cn/news/detail-500118.html

到了這里，關(guān)于ResNet代碼復(fù)現(xiàn)＋超詳細(xì)注釋（PyTorch）的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！

本文來自互聯(lián)網(wǎng)用戶投稿，該文觀點(diǎn)僅代表作者本人，不代表本站立場(chǎng)。本站僅提供信息存儲(chǔ)空間服務(wù)，不擁有所有權(quán)，不承擔(dān)相關(guān)法律責(zé)任。如若轉(zhuǎn)載，請(qǐng)注明出處： 如若內(nèi)容造成侵權(quán)/違法違規(guī)/事實(shí)不符，請(qǐng)點(diǎn)擊違法舉報(bào)進(jìn)行投訴反饋，一經(jīng)查實(shí)，立即刪除！

領(lǐng)支付寶紅包贊助服務(wù)器費(fèi)用

相關(guān)文章

覺得文章有用就打賞一下文章作者

支付寶掃一掃打賞

博客贊助

微信掃一掃打賞

請(qǐng)作者喝杯咖啡吧~博客贊助

支付寶掃一掃領(lǐng)取紅包，優(yōu)惠每天領(lǐng)

二維碼1

領(lǐng)取紅包

二維碼2

領(lǐng)紅包