Models¶
The models subpackage contains definitions for the following model architectures:
You can construct a model with random weights by calling its constructor:
import torchvision.models as models
resnet18 = models.resnet18()
alexnet = models.alexnet()
vgg16 = models.vgg16()
squeezenet = models.squeezenet1_0()
densenet = models.densenet_161()
inception = models.inception_v3()
We provide pre-trained models, using the PyTorch torch.utils.model_zoo.
These can be constructed by passing pretrained=True:
import torchvision.models as models
resnet18 = models.resnet18(pretrained=True)
alexnet = models.alexnet(pretrained=True)
squeezenet = models.squeezenet1_0(pretrained=True)
vgg16 = models.vgg16(pretrained=True)
densenet = models.densenet_161(pretrained=True)
inception = models.inception_v3(pretrained=True)
All pre-trained models expect input images normalized in the same way,
i.e. mini-batches of 3-channel RGB images of shape (3 x H x W),
where H and W are expected to be at least 224.
The images have to be loaded in to a range of [0, 1] and then normalized
using mean = [0.485, 0.456, 0.406] and std = [0.229, 0.224, 0.225].
You can use the following transform to normalize:
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
An example of such normalization can be found in the imagenet example here
ImageNet 1-crop error rates (224x224)
| Network | Top-1 error | Top-5 error |
|---|---|---|
| AlexNet | 43.45 | 20.91 |
| VGG-11 | 30.98 | 11.37 |
| VGG-13 | 30.07 | 10.75 |
| VGG-16 | 28.41 | 9.62 |
| VGG-19 | 27.62 | 9.12 |
| VGG-11 with batch normalization | 29.62 | 10.19 |
| VGG-13 with batch normalization | 28.45 | 9.63 |
| VGG-16 with batch normalization | 26.63 | 8.50 |
| VGG-19 with batch normalization | 25.76 | 8.15 |
| ResNet-18 | 30.24 | 10.92 |
| ResNet-34 | 26.70 | 8.58 |
| ResNet-50 | 23.85 | 7.13 |
| ResNet-101 | 22.63 | 6.44 |
| ResNet-152 | 21.69 | 5.94 |
| SqueezeNet 1.0 | 41.90 | 19.58 |
| SqueezeNet 1.1 | 41.81 | 19.38 |
| Densenet-121 | 25.35 | 7.83 |
| Densenet-169 | 24.00 | 7.00 |
| Densenet-201 | 22.80 | 6.43 |
| Densenet-161 | 22.35 | 6.20 |
| Inception v3 | 22.55 | 6.44 |
Alexnet¶
-
torchvision.models.alexnet(pretrained=False, **kwargs)[source]¶ AlexNet model architecture from the “One weird trick...” paper.
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
VGG¶
-
torchvision.models.vgg11(pretrained=False, **kwargs)[source]¶ VGG 11-layer model (configuration “A”)
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
-
torchvision.models.vgg11_bn(pretrained=False, **kwargs)[source]¶ VGG 11-layer model (configuration “A”) with batch normalization
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
-
torchvision.models.vgg13(pretrained=False, **kwargs)[source]¶ VGG 13-layer model (configuration “B”)
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
-
torchvision.models.vgg13_bn(pretrained=False, **kwargs)[source]¶ VGG 13-layer model (configuration “B”) with batch normalization
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
-
torchvision.models.vgg16(pretrained=False, **kwargs)[source]¶ VGG 16-layer model (configuration “D”)
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
-
torchvision.models.vgg16_bn(pretrained=False, **kwargs)[source]¶ VGG 16-layer model (configuration “D”) with batch normalization
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
ResNet¶
-
torchvision.models.resnet18(pretrained=False, **kwargs)[source]¶ Constructs a ResNet-18 model.
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
-
torchvision.models.resnet34(pretrained=False, **kwargs)[source]¶ Constructs a ResNet-34 model.
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
-
torchvision.models.resnet50(pretrained=False, **kwargs)[source]¶ Constructs a ResNet-50 model.
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
SqueezeNet¶
-
torchvision.models.squeezenet1_0(pretrained=False, **kwargs)[source]¶ SqueezeNet model architecture from the “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size” paper.
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
-
torchvision.models.squeezenet1_1(pretrained=False, **kwargs)[source]¶ SqueezeNet 1.1 model from the official SqueezeNet repo. SqueezeNet 1.1 has 2.4x less computation and slightly fewer parameters than SqueezeNet 1.0, without sacrificing accuracy.
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
DensetNet¶
-
torchvision.models.densenet121(pretrained=False, **kwargs)[source]¶ Densenet-121 model from “Densely Connected Convolutional Networks”
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
-
torchvision.models.densenet169(pretrained=False, **kwargs)[source]¶ Densenet-169 model from “Densely Connected Convolutional Networks”
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
-
torchvision.models.densenet161(pretrained=False, **kwargs)[source]¶ Densenet-161 model from “Densely Connected Convolutional Networks”
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
-
torchvision.models.densenet201(pretrained=False, **kwargs)[source]¶ Densenet-201 model from “Densely Connected Convolutional Networks”
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
Inception v3¶
-
torchvision.models.inception_v3(pretrained=False, **kwargs)[source]¶ Inception v3 model architecture from “Rethinking the Inception Architecture for Computer Vision”.
Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet