How to do handle imbalance data class while working with deep learning project in Pytorch?? I have created dataloader with Imbalanced data sets . Now what to do next. Please help me.

Here, is my code: I have created data loader with Imbalanced Dataset
from torch.utils.data import DataLoader

batch_size = 256

train_dl = DataLoader(train_ds,

                  batch_size,

                  shuffle=True,

                  num_workers=4,

                  pin_memory=True)

valid_dl = DataLoader(valid_ds,

                batch_size,

                num_workers=4,

                pin_memory=True)