Balanced Sampling between classes with torchvision DataLoader

[ptrblck]

@Griffintaur

Can’t we say it is oversampling the minority but undersampling the majority in dataset?

You could assume this, if you use the described setup.

However, you could e.g. specify replacement=False, which will return unique num_samples.
The over/undersampling also depends on the specified weights, i.e. the WeightedRandomSampler does not automatically produce equal class distributions in each batch, but you are free to specify the weights you need.