Vgg16使用和修改

羲月东辰2024-10-08 7:08

在获取vgg16网络模型参数时，获取会出错

vgg16_false = torchvision.models.vgg16(pretrained=False)

vgg16_true = torchvision.models.vgg16(pretrained=True)

修改成：

vgg16_false = torchvision.models.vgg16(weights=None)

vgg16_true = torchvision.models.vgg16(weights=VGG16_Weights.DEFAULT)

错误原因：参数pretrained自0.13起已弃用，将在0.15后删除，要改用"weights"。

Vgg16相关代码

python 复制代码

import torchvision
from torch import nn
from torchvision.models import VGG16_Weights


vgg16_false = torchvision.models.vgg16(weights=None)
vgg16_true = torchvision.models.vgg16(weights=VGG16_Weights.DEFAULT)

print(vgg16_true)

train_data=torchvision.datasets.CIFAR10('../data',train=True,transform=torchvision.transforms.ToTensor(),
                                        download=True)

# vgg16_true.add_module('add_linear',nn.Linear(1000,10))
vgg16_true.classifier.add_module('add_linear',nn.Linear(1000,10))
print(vgg16_true)

print(vgg16_false)
vgg16_false.classifier[6]=nn.Linear(4096,10)
print(vgg16_false)