Transforms: What Does the Model Actually See?

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

Here are two training runs. Same model, same data, same optimizer, same seed, same number of epochs. The preprocessing pipelines differ by one keyword argument, and neither one raises.

scale=True  input range=[   -2.12,    2.01] first_epoch_loss=   0.0001 last=   0.0000 val_acc=1.000
scale=False input range=[   -2.12,  975.64] first_epoch_loss=  36.7257 last=   1.5337 val_acc=0.620

The second pipeline produced tensors with the right shape, the right dtype, the right device, and no non-finite values. Every check from Chapter 2 passes. Every check from Chapter 5 passes. The batch arrived on time, which is everything Chapter 6 taught us to verify. And the model went from perfect to barely better than guessing.

Data Contracts on Programmer.ie

Transforms: What Does the Model Actually See?