analogvnn - v1.0.8

What's Changed

• Removed redundant code from reduce_precision.
• Added types argument to PseudoParameter.parametrize_module for better selection for Parameterising the Layers.

Full Changelog: https://github.com/Vivswan/AnalogVNN/compare/v1.0.7...v1.0.8

- Python
Published by Vivswan about 2 years ago

analogvnn - v1.0.7

What's Changed

• Fixed GeLU backward function equation.

Full Changelog: https://github.com/Vivswan/AnalogVNN/compare/v1.0.6...v1.0.7

- Python
Published by Vivswan over 2 years ago

analogvnn - v1.0.6

What's Changed

• Model is subclass of BackwardModule for additional functionality.
• Using inspect.isclass to check if backward_class is a class in Linear.set_backward_function.
• Repr using self.__class__.__name__ in all classes.

Full Changelog: https://github.com/Vivswan/AnalogVNN/compare/v1.0.5...v1.0.6

- Python
Published by Vivswan almost 3 years ago

analogvnn - v1.0.5

What's Changed (Patches for Pytorch 2.0.1)

• Patch for Pytorch 2.0.1, add filtering inputs in BackwardGraph._calculate_gradients.
• Removed unnecessary PseudoParameter.grad property.

Full Changelog: https://github.com/Vivswan/AnalogVNN/compare/v1.0.4...v1.0.5

- Python
Published by Vivswan about 3 years ago

analogvnn - v1.0.4

What's Changed

• Combined PseudoParameter and PseudoParameterModule for better visibility
  • BugFix: fixed save and load of state_dict of PseudoParameter and transformation module
• Removed redundant class analogvnn.parameter.Parameter

Full Changelog: https://github.com/Vivswan/AnalogVNN/compare/v1.0.3...v1.0.4

- Python
Published by Vivswan about 3 years ago

analogvnn - v1.0.3

What's Changed

• Added support for no loss function in Model class
  • If no loss function is provided, the Model object will use outputs for gradient computation
• Added support for multiple loss outputs from loss function

Full Changelog: https://github.com/Vivswan/AnalogVNN/compare/v1.0.2...v1.0.3

- Python
Published by Vivswan about 3 years ago

analogvnn - v1.0.2

What's Changed

• Bugfix: removed graph from Layer class
  • graph was causing issues with nested Model objects
  • Now _use_autograd_graph is directly set while compiling the Model object

Full Changelog: https://github.com/Vivswan/AnalogVNN/compare/v1.0.1...v1.0.2

- Python
Published by Vivswan about 3 years ago

analogvnn - v1.0.1

What's Changed (Patches for Pytorch 2.0.0)

• added grad.setter to PseudoParameterModule class

Full Changelog: https://github.com/Vivswan/AnalogVNN/compare/v1.0.0...v1.0.1

- Python
Published by Vivswan about 3 years ago

analogvnn - v1.0.0

Documentation: https://analogvnn.readthedocs.io/

AnalogVNN Paper: https://arxiv.org/abs/2210.10048

Cite: Vivswan Shah, and Nathan Youngblood. "AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks." *arXiv preprint arXiv:2210.10048 (2022)*.

Installation: - Install PyTorch - Install AnanlogVNN using pip bash pip install analogvnn

Full Changelog: https://github.com/Vivswan/AnalogVNN/commits/v1.0.0

- Python
Published by Vivswan about 3 years ago