WeightedRandomSampler in PyTorch_Geometric Dataloader

1

Hello everyone,

I am writing a program to perform graph classification using PyTorch Geometric, however I have a very imbalanced dataset. I was wondering if I can easily implement a method like WeightedRandomSampler in normal PyTorch?

Thanks in advance!

2

I’m not familiar with PyTorch Geometric, but in case you can precompute the targets and each sample has one corresponding target class, you could take a look at this code snippet, which explains the usage of the WeightedRandomSampler.