Skip to content

Oflibpytorch 2.0.0 - now differentiable!

Choose a tag to compare

View all tags
@CSRavasio CSRavasio released this 12 May 20:53
2.0.0
726b8f1

oflibpytorch 2.0.0 (Optical Flow Library, pytorch version)

oflib2_logo

Major update, enhancing usability for deep learning applications. Changelog:

  • Flow vectors and masks are now batched, meaning the shape is (N, H, W) instead of (H, W). This enables easy integration with any deep learning application or network, harnessing the efficiencies of batch-wise processing.
  • A differentiable PyTorch function to replace scipy.interpolate.griddata was implemented
  • A toolbox-wide boolean setting called PURE_PYTORCH has been introduced. If it is set to True, non-Torch operations are avoided as far as possible. Specifically, this means avoiding the slow Scipy-based function scipy.interpolate.griddata in favour of a more approximate, but significantly faster PyTorch-only method that interpolates unstructured data on a defined regular grid.
  • If PURE_PYTORCH is set to True, all oflibpytorch methods that output a float torch tensor are differentiable, again allowing for easy integration with deep learning algorithms.
  • Some utility functions made available
  • Documentation and unit test updates
  • Minor bugfixes
Assets 2
Loading