What is the dataset used in pre-trained VGG models?

[isaac1644 (Isaac.russell)]

The question is same to the topic. I have not found any denotations in the code showing those pre-trained models trained on which dataset .

[ptrblck]

ImageNet-12 was used to train all pre-trained models:

Using vision.models with the CIFAR dataset?

The pre-trained models are all based on Imagenet-12. Most of the model definitions also need 224x224 as the minimum input size. For CIFAR, you are better off with other repos.