GoogleNet is secretly transforming input

Hello!

I recently noticed that I might be doing image normalization twice in my experiments.
The documentation says that the default value of the transform_input parameter is False.

So when calling

model = torchvision.models.googlenet(pretrained=True)

I would probably expect the model not to do any input transformations, but accidentally it does (permalink) until you directly specify transform_input=False. So in case of pretrained=True and not-specified transform_input model suddenly sets its value to True:

    if pretrained:
        if 'transform_input' not in kwargs:
            kwargs['transform_input'] = True

It is confusing for me. This thing is only happens in GoogleNet.

Start with torchvision/models/googlenet.py at the pretrained handling around line 41, and compare it with the linked GoogleNet documentation for transform_input. Reproduce the pretrained=True case without specifying transform_input, then confirm the behavior matches the documented default and update the relevant coverage if the repository has it.