數據集下載地址：
鏈接：https://pan.baidu.com/s/1l1AnBgkAAEhh0vI5_loWKw
提取碼：2xq4
創建數據集：https://www.cnblogs.com/xiximayou/p/12398285.html
讀取數據集：https://www.cnblogs.com/xiximayou/p/12422827.html
進行訓練：https://www.cnblogs.com/xiximayou/p/12448300.html
保存模型並繼續進行訓練：https://www.cnblogs.com/xiximayou/p/12452624.html
加載保存的模型並測試：https://www.cnblogs.com/xiximayou/p/12459499.html
划分驗證集並邊訓練邊驗證：https://www.cnblogs.com/xiximayou/p/12464738.html
使用學習率衰減策略並邊訓練邊測試：https://www.cnblogs.com/xiximayou/p/12468010.html
利用tensorboard可視化訓練和測試過程：https://www.cnblogs.com/xiximayou/p/12482573.html
從命令行接收參數：https://www.cnblogs.com/xiximayou/p/12488662.html
使用top1和top5准確率來衡量模型：https://www.cnblogs.com/xiximayou/p/12489069.html
epoch、batchsize、step之間的關系：https://www.cnblogs.com/xiximayou/p/12405485.html
之前都是從頭開始訓練模型，本節我們要使用預訓練的模型來進行訓練。
只需要在train.py中加上：
if baseline: model =torchvision.models.resnet18(pretrained=False) model.fc = nn.Linear(model.fc.in_features,2,bias=False) else: print("使用預訓練的resnet18模型") model=torchvision.models.resnet18(pretrained=True) for i in model.state_dict(): print(i) model.fc = nn.Linear(model.fc.in_features,2,bias=False) print(model)
使用預訓練的resnet18模型 conv1.weight bn1.weight bn1.bias bn1.running_mean bn1.running_var bn1.num_batches_tracked layer1.0.conv1.weight layer1.0.bn1.weight layer1.0.bn1.bias layer1.0.bn1.running_mean layer1.0.bn1.running_var layer1.0.bn1.num_batches_tracked layer1.0.conv2.weight layer1.0.bn2.weight layer1.0.bn2.bias layer1.0.bn2.running_mean layer1.0.bn2.running_var layer1.0.bn2.num_batches_tracked layer1.1.conv1.weight layer1.1.bn1.weight layer1.1.bn1.bias layer1.1.bn1.running_mean layer1.1.bn1.running_var layer1.1.bn1.num_batches_tracked layer1.1.conv2.weight layer1.1.bn2.weight layer1.1.bn2.bias layer1.1.bn2.running_mean layer1.1.bn2.running_var layer1.1.bn2.num_batches_tracked layer2.0.conv1.weight layer2.0.bn1.weight layer2.0.bn1.bias layer2.0.bn1.running_mean layer2.0.bn1.running_var layer2.0.bn1.num_batches_tracked layer2.0.conv2.weight layer2.0.bn2.weight layer2.0.bn2.bias layer2.0.bn2.running_mean layer2.0.bn2.running_var layer2.0.bn2.num_batches_tracked layer2.0.downsample.0.weight layer2.0.downsample.1.weight layer2.0.downsample.1.bias layer2.0.downsample.1.running_mean layer2.0.downsample.1.running_var layer2.0.downsample.1.num_batches_tracked layer2.1.conv1.weight layer2.1.bn1.weight layer2.1.bn1.bias layer2.1.bn1.running_mean layer2.1.bn1.running_var layer2.1.bn1.num_batches_tracked layer2.1.conv2.weight layer2.1.bn2.weight layer2.1.bn2.bias layer2.1.bn2.running_mean layer2.1.bn2.running_var layer2.1.bn2.num_batches_tracked layer3.0.conv1.weight layer3.0.bn1.weight layer3.0.bn1.bias layer3.0.bn1.running_mean layer3.0.bn1.running_var layer3.0.bn1.num_batches_tracked layer3.0.conv2.weight layer3.0.bn2.weight layer3.0.bn2.bias layer3.0.bn2.running_mean layer3.0.bn2.running_var layer3.0.bn2.num_batches_tracked layer3.0.downsample.0.weight layer3.0.downsample.1.weight layer3.0.downsample.1.bias layer3.0.downsample.1.running_mean layer3.0.downsample.1.running_var layer3.0.downsample.1.num_batches_tracked layer3.1.conv1.weight layer3.1.bn1.weight layer3.1.bn1.bias layer3.1.bn1.running_mean layer3.1.bn1.running_var layer3.1.bn1.num_batches_tracked layer3.1.conv2.weight layer3.1.bn2.weight layer3.1.bn2.bias layer3.1.bn2.running_mean layer3.1.bn2.running_var layer3.1.bn2.num_batches_tracked layer4.0.conv1.weight layer4.0.bn1.weight layer4.0.bn1.bias layer4.0.bn1.running_mean layer4.0.bn1.running_var layer4.0.bn1.num_batches_tracked layer4.0.conv2.weight layer4.0.bn2.weight layer4.0.bn2.bias layer4.0.bn2.running_mean layer4.0.bn2.running_var layer4.0.bn2.num_batches_tracked layer4.0.downsample.0.weight layer4.0.downsample.1.weight layer4.0.downsample.1.bias layer4.0.downsample.1.running_mean layer4.0.downsample.1.running_var layer4.0.downsample.1.num_batches_tracked layer4.1.conv1.weight layer4.1.bn1.weight layer4.1.bn1.bias layer4.1.bn1.running_mean layer4.1.bn1.running_var layer4.1.bn1.num_batches_tracked layer4.1.conv2.weight layer4.1.bn2.weight layer4.1.bn2.bias layer4.1.bn2.running_mean layer4.1.bn2.running_var layer4.1.bn2.num_batches_tracked fc.weight fc.bias ResNet( (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) (layer1): Sequential( (0): BasicBlock( (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) (1): BasicBlock( (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (layer2): Sequential( (0): BasicBlock( (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (downsample): Sequential( (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (1): BasicBlock( (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (layer3): Sequential( (0): BasicBlock( (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (downsample): Sequential( (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (1): BasicBlock( (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (layer4): Sequential( (0): BasicBlock( (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (downsample): Sequential( (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (1): BasicBlock( (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (avgpool): AdaptiveAvgPool2d(output_size=(1, 1)) (fc): Linear(in_features=512, out_features=2, bias=False) )
接下來來看看如何凍結某些層，不讓其在訓練的時候進行梯度更新。
首先我們輸出下信息看看結構:
i=0
for child in model.children():
i+=1
print("第{}個child".format(str(i))) print(child)
第1個child Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) 第2個child BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) 第3個child ReLU(inplace=True) 第4個child MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) 第5個child Sequential( (0): BasicBlock( (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) (1): BasicBlock( (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) 第6個child Sequential( (0): BasicBlock( (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (downsample): Sequential( (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (1): BasicBlock( (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) 第7個child Sequential( (0): BasicBlock( (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (downsample): Sequential( (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (1): BasicBlock( (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) 第8個child Sequential( (0): BasicBlock( (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (downsample): Sequential( (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (1): BasicBlock( (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) 第9個child AdaptiveAvgPool2d(output_size=(1, 1)) 第10個child Linear(in_features=512, out_features=2, bias=False)
我們凍結前面的7個child，只更新第8、9、10個child的參數。可這么定義：
print("使用預訓練的resnet18模型") model=torchvision.models.resnet18(pretrained=True) model.fc = nn.Linear(model.fc.in_features,2,bias=False) i=0 for child in model.children(): i+=1 #print("第{}個child".format(str(i))) #print(child) if i<=7: for param in child.parameters(): param.requires_grad=False #我們打印下是否是設置成功 for name, param in model.named_parameters(): if param.requires_grad: print("需要梯度：", name) else: print("不需要梯度：", name)
接下來我們還要在優化器中過濾掉不需要更新參數的層：
optimizer = torch.optim.SGD(filter(lambda p: p.requires_grad, model.parameters()), lr=0.1, momentum=0.9, weight_decay=1*1e-4)
結果：
使用預訓練的resnet18模型 不需要梯度： conv1.weight 不需要梯度： bn1.weight 不需要梯度： bn1.bias 不需要梯度： layer1.0.conv1.weight 不需要梯度： layer1.0.bn1.weight 不需要梯度： layer1.0.bn1.bias 不需要梯度： layer1.0.conv2.weight 不需要梯度： layer1.0.bn2.weight 不需要梯度： layer1.0.bn2.bias 不需要梯度： layer1.1.conv1.weight 不需要梯度： layer1.1.bn1.weight 不需要梯度： layer1.1.bn1.bias 不需要梯度： layer1.1.conv2.weight 不需要梯度： layer1.1.bn2.weight 不需要梯度： layer1.1.bn2.bias 不需要梯度： layer2.0.conv1.weight 不需要梯度： layer2.0.bn1.weight 不需要梯度： layer2.0.bn1.bias 不需要梯度： layer2.0.conv2.weight 不需要梯度： layer2.0.bn2.weight 不需要梯度： layer2.0.bn2.bias 不需要梯度： layer2.0.downsample.0.weight 不需要梯度： layer2.0.downsample.1.weight 不需要梯度： layer2.0.downsample.1.bias 不需要梯度： layer2.1.conv1.weight 不需要梯度： layer2.1.bn1.weight 不需要梯度： layer2.1.bn1.bias 不需要梯度： layer2.1.conv2.weight 不需要梯度： layer2.1.bn2.weight 不需要梯度： layer2.1.bn2.bias 不需要梯度： layer3.0.conv1.weight 不需要梯度： layer3.0.bn1.weight 不需要梯度： layer3.0.bn1.bias 不需要梯度： layer3.0.conv2.weight 不需要梯度： layer3.0.bn2.weight 不需要梯度： layer3.0.bn2.bias 不需要梯度： layer3.0.downsample.0.weight 不需要梯度： layer3.0.downsample.1.weight 不需要梯度： layer3.0.downsample.1.bias 不需要梯度： layer3.1.conv1.weight 不需要梯度： layer3.1.bn1.weight 不需要梯度： layer3.1.bn1.bias 不需要梯度： layer3.1.conv2.weight 不需要梯度： layer3.1.bn2.weight 不需要梯度： layer3.1.bn2.bias 需要梯度： layer4.0.conv1.weight 需要梯度： layer4.0.bn1.weight 需要梯度： layer4.0.bn1.bias 需要梯度： layer4.0.conv2.weight 需要梯度： layer4.0.bn2.weight 需要梯度： layer4.0.bn2.bias 需要梯度： layer4.0.downsample.0.weight 需要梯度： layer4.0.downsample.1.weight 需要梯度： layer4.0.downsample.1.bias 需要梯度： layer4.1.conv1.weight 需要梯度： layer4.1.bn1.weight 需要梯度： layer4.1.bn1.bias 需要梯度： layer4.1.conv2.weight 需要梯度： layer4.1.bn2.weight 需要梯度： layer4.1.bn2.bias 需要梯度： fc.weight
拓展：如果是我們自己定義的模型和預訓練的模型不一致應該怎么加載參數呢？
這里以以resnet50為例，這里我們再新定義一個卷積神經網絡：
# coding=UTF-8 import torchvision.models as models import torch import torch.nn as nn import math import torch.utils.model_zoo as model_zoo class CNN(nn.Module): def __init__(self, block, layers, num_classes=2): self.inplanes = 64 super(ResNet, self).__init__() self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = nn.BatchNorm2d(64) self.relu = nn.ReLU(inplace=True) self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.layer1 = self._make_layer(block, 64, layers[0]) self.layer2 = self._make_layer(block, 128, layers[1], stride=2) self.layer3 = self._make_layer(block, 256, layers[2], stride=2) self.layer4 = self._make_layer(block, 512, layers[3], stride=2) self.avgpool = nn.AvgPool2d(7, stride=1) #新增一個反卷積層 self.convtranspose1 = nn.ConvTranspose2d(2048, 2048, kernel_size=3, stride=1, padding=1, output_padding=0, groups=1, bias=False, dilation=1) #新增一個最大池化層 self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1) #去掉原來的fc層，新增一個fclass層 self.fclass = nn.Linear(2048, num_classes) for m in self.modules(): if isinstance(m, nn.Conv2d): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) elif isinstance(m, nn.BatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_() def _make_layer(self, block, planes, blocks, stride=1): downsample = None if stride != 1 or self.inplanes != planes * block.expansion: downsample = nn.Sequential( nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(planes * block.expansion), ) layers = [] layers.append(block(self.inplanes, planes, stride, downsample)) self.inplanes = planes * block.expansion for i in range(1, blocks): layers.append(block(self.inplanes, planes)) 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) x = self.avgpool(x) #新加層的forward x = x.view(x.size(0), -1) x = self.convtranspose1(x) x = self.maxpool2(x) x = x.view(x.size(0), -1) x = self.fclass(x) return x #加載model resnet50 = models.resnet50(pretrained=True) cnn = CNN(Bottleneck, [3, 4, 6, 3]) #讀取參數
#取出預訓練模型的參數 pretrained_dict = resnet50.state_dict()
#取出本模型的參數 model_dict = cnn.state_dict() # 將pretrained_dict里不屬於model_dict的鍵剔除掉 pretrained_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict} # 更新現有的model_dict model_dict.update(pretrained_dict) # 加載我們真正需要的state_dict cnn.load_state_dict(model_dict) # print(resnet50) print(cnn)
下面也摘取了一些使用部分預訓練模型初始化網絡的方法：
方式一： 自己網絡和預訓練網絡結構一致的層，使用預訓練網絡對應層的參數批量初始化
model_dict = model.state_dict() # 取出自己網絡的參數字典 pretrained_dict = torch.load("I:/迅雷下載/alexnet-owt-4df8aa71.pth")# 加載預訓練網絡的參數字典 # 取出預訓練網絡的參數字典 keys = [] for k, v in pretrained_dict.items(): keys.append(k) i = 0 # 自己網絡和預訓練網絡結構一致的層，使用預訓練網絡對應層的參數初始化 for k, v in model_dict.items(): if v.size() == pretrained_dict[keys[i]].size(): model_dict[k] = pretrained_dict[keys[i]] #print(model_dict[k]) i = i + 1 model.load_state_dict(model_dict)
方式二：自己網絡和預訓練網絡結構一致的層，按層初始化
# 加粗自己定義一個網絡叫CNN model = CNN（） model_dict = model.state_dict() # 取出自己網絡的參數 for k, v in model_dict.items(): # 查看自己網絡參數各層叫什么名稱 print(k) pretrained_dict = torch.load("I:/迅雷下載/alexnet-owt-4df8aa71.pth")# 加載預訓練網絡的參數 for k, v in pretrained_dict.items(): # 查看預訓練網絡參數各層叫什么名稱 print(k) # 對應層賦值初始化 model_dict['conv1.0.weight'] = pretrained_dict['features.0.weight'] # 將自己網絡的conv1.0層的權重初始化為預訓練網絡features.0層的權重 model_dict['conv1.0.bias'] = pretrained_dict['features.0.bias'] # 將自己網絡的conv1.0層的偏置項初始化為預訓練網絡features.0層的偏置項 model_dict['conv2.1.weight'] = pretrained_dict['features.3.weight'] model_dict['conv1.1.bias'] = pretrained_dict['features.3.bias'] model_dict['conv2.1.weight'] = pretrained_dict['features.6.weight'] model_dict['conv2.1.bias'] = pretrained_dict['features.6.bias'] ... ...
下一節補充下計算數據集的標准差和方差，在數據增強時對數據進行標准化的時候用。
參考：
https://blog.csdn.net/feizai1208917009/article/details/103598233