Oflibpytorch 2.1.1

oflibpytorch 2.1.1 (Optical Flow Library, pytorch version)

Changelog:

• Flow method 'unpad' introduced: effectively a helper function to undo Flow.pad
• Flow method 'from_transforms' signature extended by a padding argument: convenience when creating
  a padded flow field, automatically adjusting the shape and relevant transform parameters
• Flow method 'select' parameter item can be None, returning self
• Flow method 'get_padding' signature extended by an item argument, used to select an item in the
  batched flow. Returns a simple list of padding values, rather than a list of lists.
• Minor performance improvement in Flow method 'combine'

Oflibpytorch 2.1.0

oflibpytorch 2.1.0 (Optical Flow Library, pytorch version)

Changelog:

• Flow method 'combine' introduced: efficient, generalised combination of flows with any frame of reference
• Flow method 'combine_with' improved, but will become deprecated in a future release in favour of 'combine'
• Test coverage improved
• Documentation updated and extended

Oflibpytorch 2.0.0 - now differentiable!

oflibpytorch 2.0.0 (Optical Flow Library, pytorch version)

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

Oflibpytorch 1.1.1

oflibpytorch 1.1.1 (Optical Flow Library, pytorch version)

Changelog:

• Type of the flow attribute 'device' changed from string to the torch.device class
• If the CUDA device index is left undefined, it defaults to torch.cuda.current_device(). This avoids ambiguities
  and possible CUDA device mismatches when working with multiple GPUs.

Oflibpytorch 1.1.0

oflibpytorch 1.1.0 (Optical Flow Library, pytorch version)

Changelog:

• Introduced functions that largely replicate functionality of flow class methods, but for Torch tensor and NumPy array flow inputs
• Documentation updated with above functions, some older errors corrected
• Minor bugfixes
• Bibtex citation to use to acknowledge the authors added

Oflibpytorch 1.0.1

Patch version update, oflibpytorch 1.0.1

• Fixed bug in visualise (range_max calculation)
• Removed all usages of the torch tensor attribute "ndim" for improved backwards compatibility with older torch
  versions.
• Removed print statement in test_utils
• Minor documentation corrections, addition of this changelog

Oflibpytorch 1.0.0

First release of oflibpytorch (Optical Flow Library, pytorch version)