TORCHVISION MODELS

随机weights创建model

import torchvision.models as models
resnet18 = models.resnet18()
alexnet = models.alexnet()
vgg16 = models.vgg16()
squeezenet = models.squeezenet1_0()
densenet = models.densenet161()
inception = models.inception_v3()
googlenet = models.googlenet()
shufflenet = models.shufflenet_v2_x1_0()
mobilenet = models.mobilenet_v2()
resnext50_32x4d = models.resnext50_32x4d()
wide_resnet50_2 = models.wide_resnet50_2()
mnasnet = models.mnasnet1_0()

pre-trained创建model

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.densenet161(pretrained=True)
inception = models.inception_v3(pretrained=True)
googlenet = models.googlenet(pretrained=True)
shufflenet = models.shufflenet_v2_x1_0(pretrained=True)
mobilenet = models.mobilenet_v2(pretrained=True)
resnext50_32x4d = models.resnext50_32x4d(pretrained=True)
wide_resnet50_2 = models.wide_resnet50_2(pretrained=True)
mnasnet = models.mnasnet1_0(pretrained=True)

这些权重系数将被保存在.cache\torch\checkpoints\中，通过TORCH_MODEL_ZOO来更改。
一些模型坑你有不同的训练与验证的行为，比如batch normalization。所以在不同的modes中切换，使用mode.train()和model.eval()
所有的pre-trained模型传入的图像都是经过normalized，比如mini-batches of 3-channel RGB(3HW)，图像会被normalized成[0,1]，然后使用mean=[0.485,0.456,0.406]和std = [0.299,0.244,0.225]

normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                 std=[0.229, 0.224, 0.225])

import torch
from torchvision import datasets, transforms as T

transform = T.Compose([T.Resize(256), T.CenterCrop(224), T.ToTensor()])
dataset = datasets.ImageNet(".", split="train", transform=transform)

means = []
stds = []
for img in subset(dataset):
    means.append(torch.mean(img))
    stds.append(torch.std(img))

mean = torch.mean(torch.tensor(means))
std = torch.mean(torch.tensor(stds))

参考：
https://pytorch.org/docs/stable/torchvision/models.html