π Geometric Computer Vision Library for Spatial AI
Python artificial-intelligencecomputer-visiondeep-learninghacktoberfestimage-processingmachine-learningneural-networkpythonpytorchroboticsspatial-ai
Layers and other models
=======================
.. currentmodule:: kornia.feature
Layers
------
:class:`FilterResponseNorm2d` and :class:`TLU` are the normalisation and activation layers of :class:`HyNet`,
from the Filter Response Normalization paper. They take a ``(B, num_features, H, W)`` feature map and use no
batch statistics.
.. autoclass:: FilterResponseNorm2d
.. autoclass:: TLU
Fast moving objects
-------------------
:class:`DeFMO` deblurs a fast-moving object, given the blurred image and an estimate of its background, into 24
RGBA sub-frames of the object alone.
.. autoclass:: DeFMO
:members: forward