search

gotjd709 / hooknet

1 stars 1 forks source link

Fixed augmentation for patch image? #2

Open zhujingsong opened 2 years ago

zhujingsong commented 2 years ago

Normally we will put the augmentation part in the def getitem(self, index) of class TensorData_scale(Dataset), so that for every epoch, a different kind of augmentation could be applied to [img1, img2, mask].

I found that you did the augmentation before def getitem(self, index) and saved it as a fixed numpy array. I assume possibly such a data loading way might cause out of memory problem and fixed augmentation for patch image in every epoch.

gotjd709 commented 2 years ago

Thanks so much for the advice on getitem(self, index). I have been unaware of this part. And now that I know, I have edited the code.

I really appreciate your interest in my code.