# torchvision.models # torchvision.models `torchvision.models`模块的 子模块中包含以下模型结构。 - AlexNet - VGG - ResNet - SqueezeNet - DenseNet You can construct a model with random weights by calling its constructor: 你可以使用随机初始化的权重来创建这些模型。 ``` import torchvision.models as models resnet18 = models.resnet18() alexnet = models.alexnet() squeezenet = models.squeezenet1_0() densenet = models.densenet_161() ``` We provide pre-trained models for the ResNet variants and AlexNet, using the PyTorch torch.utils.model\_zoo. These can constructed by passing pretrained=True: 对于`ResNet variants`和`AlexNet`，我们也提供了预训练(`pre-trained`)的模型。 ``` import torchvision.models as models #pretrained=True就可以使用预训练的模型 resnet18 = models.resnet18(pretrained=True) alexnet = models.alexnet(pretrained=True) ``` ImageNet 1-crop error rates (224x224) NetworkTop-1 errorTop-5 errorResNet-1830.2410.92ResNet-3426.708.58ResNet-5023.857.13ResNet-10122.636.44ResNet-15221.695.94Inception v322.556.44AlexNet43.4520.91VGG-1130.9811.37VGG-1330.0710.75VGG-1628.419.62VGG-1927.629.12SqueezeNet 1.041.9019.58SqueezeNet 1.141.8119.38Densenet-12125.357.83Densenet-16924.007.00Densenet-20122.806.43Densenet-16122.356.20## torchvision.models.alexnet(pretrained=False, \*\* kwargs) `AlexNet` 模型结构 [paper地址](https://arxiv.org/abs/1404.5997) - pretrained (bool) – `True`, 返回在ImageNet上训练好的模型。 ## torchvision.models.resnet18(pretrained=False, \*\* kwargs) 构建一个`resnet18`模型 - pretrained (bool) – `True`, 返回在ImageNet上训练好的模型。 ## torchvision.models.resnet34(pretrained=False, \*\* kwargs) 构建一个`ResNet-34` 模型. Parameters: pretrained (bool) – `True`, 返回在ImageNet上训练好的模型。 ## torchvision.models.resnet50(pretrained=False, \*\* kwargs) 构建一个`ResNet-50`模型 - pretrained (bool) – `True`, 返回在ImageNet上训练好的模型。 ## torchvision.models.resnet101(pretrained=False, \*\* kwargs) Constructs a ResNet-101 model. - pretrained (bool) – `True`, 返回在ImageNet上训练好的模型。 ## torchvision.models.resnet152(pretrained=False, \*\* kwargs) Constructs a ResNet-152 model. - pretrained (bool) – `True`, 返回在ImageNet上训练好的模型。 ## torchvision.models.vgg11(pretrained=False, \*\* kwargs) VGG 11-layer model (configuration “A”) - pretrained (bool) – `True`, 返回在ImageNet上训练好的模型。 ## torchvision.models.vgg11\_bn(\*\* kwargs) VGG 11-layer model (configuration “A”) with batch normalization ## torchvision.models.vgg13(pretrained=False, \*\* kwargs) VGG 13-layer model (configuration “B”) - pretrained (bool) – `True`, 返回在ImageNet上训练好的模型。 ## torchvision.models.vgg13\_bn(\*\* kwargs) VGG 13-layer model (configuration “B”) with batch normalization ## torchvision.models.vgg16(pretrained=False, \*\* kwargs) VGG 16-layer model (configuration “D”) Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet ## torchvision.models.vgg16\_bn(\*\* kwargs) VGG 16-layer model (configuration “D”) with batch normalization ## torchvision.models.vgg19(pretrained=False, \*\* kwargs) VGG 19-layer model (configuration “E”) - pretrained (bool) – `True`, 返回在ImageNet上训练好的模型。## torchvision.models.vgg19\_bn(\*\* kwargs) VGG 19-layer model (configuration ‘E’) with batch normalization