Chapter05: VGG_architecture runs without warning and errors in Google Colab but not Jupyter Notebooks

[Br4dski]

Hi,
I have downloaded the code for VGG_architecture and when I try to run in Jupyter Notebooks I get warnings and errors, but running in Colab works fine.

The warnings / errors in Jupyter Notebooks are the following:

1. When I run the cell that contains "model = models.vgg16(pretrained=True).to(device)" I get this warning:
   a. "C:\Users\brad_\AppData\Roaming\Python\Python312\site-packages\torchvision\models_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
   warnings.warn(
   C:\Users\brad_\AppData\Roaming\Python\Python312\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=VGG16_Weights.IMAGENET1K_V1. You can also use weights=VGG16_Weights.DEFAULT to get the most up-to-date weights.
   warnings.warn(msg)"
2. Then when the next cell runs "summary(model, torch.zeros(1,3,224,224));", I get the following warning:
   a. ---> 31 summary(model, torch.zeros(1,3,224,224))
   b. TypeError: rand(): argument 'size' failed to unpack the object at pos 2 with error "type must be tuple of ints,but got Tensor"

Can someone please explain why I'm getting this, I would like to have these example codes running in Jupyter Notebook?

Regards
Brad

[Br4dski]

Any update here please?