Custom data transforms

Customize how your data is processed to better fit your needs.

Subclass the StreamingDataset and override its getitem method to add any extra data transformations.

from litdata import StreamingDataset, StreamingDataLoader
import torchvision.transforms.v2.functional as F

class ImagenetStreamingDataset(StreamingDataset):

    def __getitem__(self, index):
        image = super().__getitem__(index)
        return F.resize(image, (224, 224))

dataset = ImagenetStreamingDataset(...)
dataloader = StreamingDataLoader(dataset, batch_size=4)

for batch in dataloader:
    print(batch.shape)
    # Out: (4, 3, 224, 224)

Was this page helpful?