Some confusion about the data preprocessing.

[clks-wzz]

I found that the "preocessing.py" codes use a simple transforms.RandomResizedCrop(224) to preprocess the input training data. Why don't you utilize aspect preserving resize before cropping? Thanks.

[leaderj1001]

Thanks for your opinion. I refer to the following URL. but, I think when we using a RandomResizedCrop(224), it can get a generalized effect. pytorch example

Thank you :)