Refactor #149
Merged
Refactor #149
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…alidating results against Autolirpa using various LIRPA methods.
…ation via layer_backward - Introduced the DecomonLinear class for streamlined handling of linear operations. - Updated the Reshape implementation to use DecomonLinear, improving modularity and consistency. - Enabled affine propagation through the layer_backward method, leveraging the jacobinet library for enhanced computational efficiency.
…tency - Updated DecomonFlatten to inherit from DecomonLinearLayer instead of its previous base. - Improves code structure and aligns with the updated design pattern for linear layers.
- Updated assert statements to accept decimal as an argument. - Improves flexibility and allows custom precision levels for tests.
…sistency - Updated DecomonCropping2D to inherit from DecomonLinearLayer instead of its previous base. - Improves code structure and aligns with the updated design pattern for linear layers.
…sistency - Updated DecomonCropping3D to inherit from DecomonLinearLayer instead of its previous base. - Improves code structure and aligns with the updated design pattern for linear layers.
…sistency - Updated DecomonCropping1D to inherit from DecomonLinearLayer instead of its previous base. - Improves code structure and aligns with the updated design pattern for linear layers.
…consistency - Updated DecomonZeroPadding2Dto inherit from DecomonLinearLayer instead of its previous base. - Improves code structure and aligns with the updated design pattern for linear layers.
…consistency - Updated DecomonZeroPadding1Dto inherit from DecomonLinearLayer instead of its previous base. - Improves code structure and aligns with the updated design pattern for linear layers.
…consistency - Updated DecomonZeroPadding3D to inherit from DecomonLinearLayer instead of its previous base. - Improves code structure and aligns with the updated design pattern for linear layers.
…ency - Updated DecomonConv2D to inherit from DecomonLinearLayer instead of its previous base, improving code structure and aligning with the updated design pattern for linear layers. - Created a dedicated test for the updated implementation. - Implemented on-the-fly creation of layer_pos and layer_neg using the Conv_kernel_constraint subclass to optimize forward_ibp.
Add the import into init.py files on modules convolutional and layers Modify the inheritance of Conv_kernel_constraint to use BaseConv instead of a general Layer Create unit test’
Add the import into init.py files on modules convolutional and layers Implement DepthwiseConv_kernel_constraint and use DepthwiseBaseConv instead of a general Layer Create unit test’
- Corrected output_shape calculation by replacing output_shape=depth_multiplier*input_shape[0] with input_shape[0].
Add the import into init.py files on modules convolutional and layers Modify check_layer to change axis in 3D tensor parameters Create unit test’
…ance - Updated DecomonDense to inherit from DecomonLinearLayer for improved consistency and modularity. - Created Dense_kernel_constraint to enable the creation of an increasing dense layer and a decreasing dense layer with shared weights.
… working on MPS due to unsupported linear.solve.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.