Normalice y estandarice las entradas

Features on wildly different scales, like age and salary, confuse a network. Rescaling them first is why normalization makes training converge faster. ⚖️

You will meet two main scalers: standardization shifts data to mean zero and unit variance, while min-max squeezes it into a fixed range like 0 to 1.

Standardization subtracts the mean and divides by the standard deviation. The result is centered on zero with a spread of one, the deep learning default.

Min-max scaling maps your smallest value to 0 and largest to 1. It is handy when a bounded input range matters, like pixel intensities.

Compute the mean and std from the training set only. Reusing test data to set these stats leaks information and inflates your scores.

Apply the exact training statistics to validation and test data. Both splits must be transformed the same way or your model sees mismatched inputs.

For images you normalize each color channel with its own mean and std. PyTorch ships transforms.Normalize to do exactly this in a pipeline.

When using pretrained vision models, normalize with the ImageNet means and stds they were trained on. Matching those numbers keeps inputs in the expected range.

The cleanest spot to scale is your dataset's __getitem__ or a transform. Then every sample arrives normalized without extra code in your training loop.

If a feature is constant its std is zero and dividing explodes. Add a tiny epsilon to the denominator to keep the math safe and stable.

Normalizing inputs is a quick preprocessing habit, yet it often unlocks faster, more stable training. Skip it and even a good model may crawl.

From which split should you compute normalization statistics?

Normalization rescales features so training converges, using stats fit on the training set and reused everywhere, often inside a transform. 🎉