https://www.bilibili.com/video/BV1T7411T7wa
分析ResNet網絡的結構，了解Batch Normalization和遷移學習的相關概念

不能簡單堆疊cnn與pool：效果差了
1.梯度消失與爆炸明顯
消失：

解決：數據標準化處理，模型初始化，以及BatchNormalization
2.退化的問題
用殘差結構解決

兩種殘差結構：左面的給小的，右邊的給大的

7：35 很詳細

下采樣（用右邊的卷積核降維）

遷移學習：
31：58

model

import torch.nn as nn import torchclass BasicBlock(nn.Module):expansion = 1#stride，實線為1 虛線為2 05：04def __init__(self, in_channel, out_channel, stride=1, downsample=None):super(BasicBlock, self).__init__()self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,kernel_size=3, stride=stride, padding=1, bias=False)#bias 不需要使用偏置self.bn1 = nn.BatchNorm2d(out_channel)self.relu = nn.ReLU()self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,kernel_size=3, stride=1, padding=1, bias=False)self.bn2 = nn.BatchNorm2d(out_channel)self.downsample = downsample#對應虛線的殘差結構def forward(self, x):identity = x#捷徑的輸出值if self.downsample is not None:identity = self.downsample(x)out = self.conv1(x)out = self.bn1(out)out = self.relu(out)out = self.conv2(out)out = self.bn2(out)out += identityout = self.relu(out)return outclass Bottleneck(nn.Module):#50，101，152的殘差結構expansion = 4#4倍def __init__(self, in_channel, out_channel, stride=1, downsample=None):super(Bottleneck, self).__init__()self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,kernel_size=1, stride=1, bias=False) # squeeze channelsself.bn1 = nn.BatchNorm2d(out_channel)# -----------------------------------------self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,kernel_size=3, stride=stride, bias=False, padding=1)self.bn2 = nn.BatchNorm2d(out_channel)# -----------------------------------------self.conv3 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel*self.expansion,kernel_size=1, stride=1, bias=False) # unsqueeze channels#out*expansion = 4#4倍self.bn3 = nn.BatchNorm2d(out_channel*self.expansion)self.relu = nn.ReLU(inplace=True)self.downsample = downsampledef forward(self, x):identity = xif self.downsample is not None:identity = self.downsample(x)out = self.conv1(x)out = self.bn1(out)out = self.relu(out)out = self.conv2(out)out = self.bn2(out)out = self.relu(out)out = self.conv3(out)out = self.bn3(out)out += identityout = self.relu(out)return outclass ResNet(nn.Module):def __init__(self, block, blocks_num, num_classes=1000, include_top=True):super(ResNet, self).__init__()self.include_top = include_topself.in_channel = 64self.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2,padding=3, bias=False)self.bn1 = nn.BatchNorm2d(self.in_channel)self.relu = nn.ReLU(inplace=True)self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.layer1 = self._make_layer(block, 64, blocks_num[0])self.layer2 = self._make_layer(block, 128, blocks_num[1], stride=2)self.layer3 = self._make_layer(block, 256, blocks_num[2], stride=2)self.layer4 = self._make_layer(block, 512, blocks_num[3], stride=2)if self.include_top:self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) # output size = (1, 1)self.fc = nn.Linear(512 * block.expansion, num_classes)for m in self.modules():if isinstance(m, nn.Conv2d):nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')def _make_layer(self, block, channel, block_num, stride=1):downsample = Noneif stride != 1 or self.in_channel != channel * block.expansion:downsample = nn.Sequential(nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False),nn.BatchNorm2d(channel * block.expansion))layers = []layers.append(block(self.in_channel, channel, downsample=downsample, stride=stride))self.in_channel = channel * block.expansionfor _ in range(1, block_num):layers.append(block(self.in_channel, channel))return nn.Sequential(*layers)def forward(self, x):x = self.conv1(x)x = self.bn1(x)x = self.relu(x)x = self.maxpool(x)x = self.layer1(x)x = self.layer2(x)x = self.layer3(x)x = self.layer4(x)if self.include_top:x = self.avgpool(x)x = torch.flatten(x, 1)x = self.fc(x)return xdef resnet34(num_classes=2, include_top=True):return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)def resnet101(num_classes=2, include_top=True):return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top)

train

net = resnet34() # load pretrain weights # model_weight_path = "./resnet34-pre.pth" # missing_keys, unexpected_keys = net.load_state_dict(torch.load(model_weight_path), strict=False) # for param in net.parameters(): # param.requires_grad = False # change fc layer structure inchannel = net.fc.in_features net.fc = nn.Linear(inchannel, 2) net.to(device)loss_function = nn.CrossEntropyLoss() optimizer = optim.Adam(net.parameters(), lr=0.0001)

總結

以上是生活随笔為你收集整理的ResNet学习笔记的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。