deepinv.transform#
This module contains different transforms which can be used for data augmentation or together with the equivariant losses. Please refer to the user guide for more information.
Base class#
User Guide: refer to Transforms for more information.
Base class for image transforms. |
Simple transforms#
2D Rotations. |
|
Fast integer 2D translations. |
|
2D Scaling. |
|
Reflect (flip) in random multiple axes. |
Advanced transforms#
Random projective transformations (homographies). |
|
Random Euclidean image transformations using projective transformation framework. |
|
Random 2D similarity image transformations using projective transformation framework. |
|
Random affine image transformations using projective transformation framework. |
|
Random 3D camera rotation image transformations using projective transformation framework. |
|
Continuous Piecewise-Affine-based Diffeomorphism. |
Video transforms#
While all geometric transforms accept video input, the following transforms work specifically in the time dimension.
These can be easily compounded with geometric transformations using the *
operation.
Shift a video in time with reflective padding. |