deep learning RMSE and loss

Why VDSR change the input layer size(training patch size), the RMSE is different during training

Answer 1

[Mahesh Taparia]

Hi

The inbuilt trained VDSR model is having a size of 41X41X1. But you can change the input size and retrain the VDSR model. For more information, you can refer to the documenation of VDSR. Hope it will help.