About The Experiment on CIFAR10 about edesc-pytorch HOT 1 OPEN

mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
@torch.no_grad()
def CIFAR10_features():
    transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize(mean, std)])
    cifar10 = torchvision.datasets.CIFAR10(root='/home/mxh/datasets/CIFAR10',train=True,download=False,transform=transform)
    trainloader = torch.utils.data.DataLoader(cifar10, batch_size=2048, shuffle=True, num_workers=2)
    model = torchvision.models.resnet50(weights='DEFAULT')
    model.eval()
    model.fc= torch.nn.Identity()
    img_list = []
    label_list = []
    for img,label in trainloader:
        img_list.append(model(img))
        label_list.append(label)
    cifar10 = torchvision.datasets.CIFAR10(root='/home/mxh/datasets/CIFAR10',train=False,download=False,transform=transform)
    testloader = torch.utils.data.DataLoader(cifar10, batch_size=2048, shuffle=True, num_workers=2)
    for img,label in testloader:
        img_list.append(model(img))
        label_list.append(label)
    img_list = torch.cat(img_list, dim=0).numpy()
    label_list = torch.cat(label_list, dim=0).numpy()
    data = {'data':img_list, 'label':label_list}
    np.save("/home/mxh/codes/EDESC-pytorch-master/data/CIFAR10/cifar.npy", data)