Custom Surrogate Gradient Function #237
Merged
Conversation
This file contains 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
CustomSurrogate class and custom_surrogate function added to the surrogate.py file. This enables the users to define their own custom surrogate function and call it using either custom_surrogate(name_of_custom_surrogate_function) or CustomSurrogate.apply(data, name_of_custom_surrogate_function) The arguments of the custom surrogate gradient function always are The input of the forward pass (input_), the gradient of the input (grad_input) and the output of the the forward pass (out) respectively. ** Important Note: The hyperparameters of the custom Surrogate gradient function have to be defined inside of the function itself. **
|
This is really elegant, thanks for this contribution! I've just done a commit to fix up some minor docstrings, and also added a section in the documentation about custom surrogate gradients. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
CustomSurrogate class and custom_surrogate function added to the surrogate.py file.
This enables the users to define their own custom surrogate function and call it using either custom_surrogate(name_of_custom_surrogate_function) or
CustomSurrogate.apply(data, name_of_custom_surrogate_function)
The arguments of the custom surrogate gradient function always are The input of the forward pass (input_), the gradient of the input (grad_input) and the output of the the forward pass (out) respectively.
** Important Note: The hyperparameters of the custom Surrogate gradient function have to be defined inside of the function itself. **