liveBook · Manning

Mirror

Mirroring is a transformation that reverses an image or array along one or more dimensions to produce a reflected variant.

How 2 Manning books explain it

Deep Learning with JAX

An array or image transformation that reverses the order of elements along a chosen dimension.

How it is used
Applies horizontal image reversal during preprocessing and randomized data augmentation.
How deep it goes
Explains axis selection and provides slicing and NumPy alternatives, but does not develop implementation internals.
Examples
Uses a cat image, horizontal pixel reversal, and a cat-and-dog classification augmentation pipeline.
What you can do after
Apply it via array slicing or NumPy flip() to reverse an image dimension.

Read how Deep Learning with JAX explains mirror →

Deep Learning with PyTorch, Second Edition

An augmentation operation that flips an input to create a reflected variant.

How it is used
Uses reflection to expand training data while preserving a sample’s representative content.
How deep it goes
Explains axis choice, pixel preservation, random selection, and caching order, but defers broader augmentation mechanics.
Examples
Demonstrates up-down, left-right, and front-back flips, including randomized CT-axis flips in PyTorch.
What you can do after
Apply it via PyTorch augmentation code by randomly negating selected transformation-matrix axes.

Read how Deep Learning with PyTorch, Second Edition explains mirror →

Related concepts

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.