总结：如何获取模型的某一层

就是使用"."和[i]这两种方式获取&＃xff0c;可以先把网络打印出来&＃xff0c;然后再写。一般就是看到数字就用[i]&＃xff0c;看到名字&＃xff0c;就用"."来获取。

比如&＃xff1a;alexnet模型

import torchvision.models as modelsmodel &＃61; models.alexnet(pretrained&＃61;False)
print(model)


结果为&＃xff1a;

D:\Anaconda3\envs\pytorch_env\python.exe D:/pythonCodes/深度学习实验/经典分类网络/finetune代码汇总/test2.py
AlexNet((features): Sequential((0): Conv2d(3, 64, kernel_size&＃61;(11, 11), stride&＃61;(4, 4), padding&＃61;(2, 2))(1): ReLU(inplace&＃61;True)(2): MaxPool2d(kernel_size&＃61;3, stride&＃61;2, padding&＃61;0, dilation&＃61;1, ceil_mode&＃61;False)(3): Conv2d(64, 192, kernel_size&＃61;(5, 5), stride&＃61;(1, 1), padding&＃61;(2, 2))(4): ReLU(inplace&＃61;True)(5): MaxPool2d(kernel_size&＃61;3, stride&＃61;2, padding&＃61;0, dilation&＃61;1, ceil_mode&＃61;False)(6): Conv2d(192, 384, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1))(7): ReLU(inplace&＃61;True)(8): Conv2d(384, 256, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1))(9): ReLU(inplace&＃61;True)(10): Conv2d(256, 256, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1))(11): ReLU(inplace&＃61;True)(12): MaxPool2d(kernel_size&＃61;3, stride&＃61;2, padding&＃61;0, dilation&＃61;1, ceil_mode&＃61;False))(avgpool): AdaptiveAvgPool2d(output_size&＃61;(6, 6))(classifier): Sequential((0): Dropout(p&＃61;0.5, inplace&＃61;False)(1): Linear(in_features&＃61;9216, out_features&＃61;4096, bias&＃61;True)(2): ReLU(inplace&＃61;True)(3): Dropout(p&＃61;0.5, inplace&＃61;False)(4): Linear(in_features&＃61;4096, out_features&＃61;4096, bias&＃61;True)(5): ReLU(inplace&＃61;True)(6): Linear(in_features&＃61;4096, out_features&＃61;1000, bias&＃61;True))
)Process finished with exit code 0


例1&＃xff1a;获取classifier()

import torchvision.models as modelsmodel &＃61; models.alexnet(pretrained&＃61;False)
print(model.classifier)

结果&＃xff1a;

例2&＃xff1a;获取classifier()的最后一个Linear层

import torchvision.models as modelsmodel &＃61; models.alexnet(pretrained&＃61;False)
print(model.classifier[6])

结果&＃xff1a;

例3&＃xff1a;获取classifier()的最后一个Linear层的输入参数的个数

import torchvision.models as modelsmodel &＃61; models.alexnet(pretrained&＃61;False)
print(model.classifier[6].in_features)

结果&＃xff1a;

 再比如&＃xff0c;resnet模型

import torchvision.models as modelsmodel &＃61; models.resnet18(pretrained&＃61;False)
print(model)

结果&＃xff1a;

D:\Anaconda3\envs\pytorch_env\python.exe D:/pythonCodes/深度学习实验/经典分类网络/finetune代码汇总/test2.py
ResNet((conv1): Conv2d(3, 64, kernel_size&＃61;(7, 7), stride&＃61;(2, 2), padding&＃61;(3, 3), bias&＃61;False)(bn1): BatchNorm2d(64, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(relu): ReLU(inplace&＃61;True)(maxpool): MaxPool2d(kernel_size&＃61;3, stride&＃61;2, padding&＃61;1, dilation&＃61;1, ceil_mode&＃61;False)(layer1): Sequential((0): BasicBlock((conv1): Conv2d(64, 64, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn1): BatchNorm2d(64, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(relu): ReLU(inplace&＃61;True)(conv2): Conv2d(64, 64, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn2): BatchNorm2d(64, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True))(1): BasicBlock((conv1): Conv2d(64, 64, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn1): BatchNorm2d(64, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(relu): ReLU(inplace&＃61;True)(conv2): Conv2d(64, 64, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn2): BatchNorm2d(64, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)))(layer2): Sequential((0): BasicBlock((conv1): Conv2d(64, 128, kernel_size&＃61;(3, 3), stride&＃61;(2, 2), padding&＃61;(1, 1), bias&＃61;False)(bn1): BatchNorm2d(128, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(relu): ReLU(inplace&＃61;True)(conv2): Conv2d(128, 128, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn2): BatchNorm2d(128, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(downsample): Sequential((0): Conv2d(64, 128, kernel_size&＃61;(1, 1), stride&＃61;(2, 2), bias&＃61;False)(1): BatchNorm2d(128, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)))(1): BasicBlock((conv1): Conv2d(128, 128, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn1): BatchNorm2d(128, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(relu): ReLU(inplace&＃61;True)(conv2): Conv2d(128, 128, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn2): BatchNorm2d(128, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)))(layer3): Sequential((0): BasicBlock((conv1): Conv2d(128, 256, kernel_size&＃61;(3, 3), stride&＃61;(2, 2), padding&＃61;(1, 1), bias&＃61;False)(bn1): BatchNorm2d(256, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(relu): ReLU(inplace&＃61;True)(conv2): Conv2d(256, 256, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn2): BatchNorm2d(256, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(downsample): Sequential((0): Conv2d(128, 256, kernel_size&＃61;(1, 1), stride&＃61;(2, 2), bias&＃61;False)(1): BatchNorm2d(256, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)))(1): BasicBlock((conv1): Conv2d(256, 256, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn1): BatchNorm2d(256, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(relu): ReLU(inplace&＃61;True)(conv2): Conv2d(256, 256, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn2): BatchNorm2d(256, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)))(layer4): Sequential((0): BasicBlock((conv1): Conv2d(256, 512, kernel_size&＃61;(3, 3), stride&＃61;(2, 2), padding&＃61;(1, 1), bias&＃61;False)(bn1): BatchNorm2d(512, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(relu): ReLU(inplace&＃61;True)(conv2): Conv2d(512, 512, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn2): BatchNorm2d(512, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(downsample): Sequential((0): Conv2d(256, 512, kernel_size&＃61;(1, 1), stride&＃61;(2, 2), bias&＃61;False)(1): BatchNorm2d(512, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)))(1): BasicBlock((conv1): Conv2d(512, 512, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn1): BatchNorm2d(512, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)(relu): ReLU(inplace&＃61;True)(conv2): Conv2d(512, 512, kernel_size&＃61;(3, 3), stride&＃61;(1, 1), padding&＃61;(1, 1), bias&＃61;False)(bn2): BatchNorm2d(512, eps&＃61;1e-05, momentum&＃61;0.1, affine&＃61;True, track_running_stats&＃61;True)))(avgpool): AdaptiveAvgPool2d(output_size&＃61;(1, 1))(fc): Linear(in_features&＃61;512, out_features&＃61;1000, bias&＃61;True)
)Process finished with exit code 0

想获取layer4的第0块的downsample的第0块的Conv2d层&＃xff1a;

import torchvision.models as modelsmodel &＃61; models.resnet18(pretrained&＃61;False)
print(model.layer4[0].downsample[0])

结果&＃xff1a;