Some confusion about the data preprocessing.

leaderj1001 / MobileNetV3-Pytorch

Implementing Searching for MobileNetV3 paper using Pytorch

MIT License

292 stars 70 forks source link

Some confusion about the data preprocessing. #12

Open clks-wzz opened 5 years ago

clks-wzz commented 5 years ago

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 commented 5 years ago

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 :)