PyTorch Transforms: From Raw Data to the Tensor Your Model Actually Sees

Sat, 22 Aug 2026 11:58:00 +0100

PyTorch From First Principles — Interlude 05A

In the previous chapter we treated the DataLoader as a production system.

It reads samples, prepares batches, moves work through worker processes and tries to keep the accelerator fed.

But there is a question hiding inside that pipeline:

What exactly is a sample by the time the model receives it?

A file on disk is not usually the tensor the model trains on.