Yiming Ma

Hi @learningelectric, MobileNetV2 blocks reduce the height & weight of input by 2. It seems like you only need to resize input images so that the these two quantities can...

Hi @learningelectric, With pleasure to help. I guess you are following this tutorial provided by PyTorch [Training a classifier](https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html). If so, you only need to add `torchvision.transforms.Resize` to the original...

Hi @Viresh-R and @gshoai , I have the same question. Is it possible to provide the original dataset? Reducing image sizes may lose important info in dense areas and thus...

Why you installed an incompatible version of CUDNN? Currently, there is no cudnn-11.2 in the repository, so you might want to downgrade your CUDA version to 11.1 and install ```system76-cudnn-11.1```....

I got this error as well when I was trying to send my fourth message in a thread.

I am also interested to see what's the optimal setup for hyper-parameters like the learning rate, weight decay, and scheduling scheme.