在 PyTorch 中加载 resnet50 prettriated model

Question

I want to use resnet50 pretrained model using PyTorch and I am using the following code for loading it:

    import torch
    model = torch.hub.load("pytorch/vision", "resnet50", weights="IMAGENET1K_V2")

Although I upgrade the torchvision but I receive the following error:

Any idea?

Answer 1

As per the latest definition, we now load models using torchvision library, you can try that using:

from torchvision.models import resnet50, ResNet50_Weights

# Old weights with accuracy 76.130%
model1 = resnet50(weights=ResNet50_Weights.IMAGENET1K_V1)

# New weights with accuracy 80.858%
model2 = resnet50(weights=ResNet50_Weights.IMAGENET1K_V2)