Tensor support for wmin/wmax #509
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
Kwarg wmin/wmax change (test commit)
- wmin/wmax needed in parameters to interact with w (which may be moved to a different device with the module).
…s a small clarification on its documentation)
…ionality for tensor wmin/wmax in SparseConnection
…ng functionality for tensor wmin/wmax in SparseConnection" This reverts commit 78596e3.
…ing adding functionality for tensor wmin/wmax in SparseConnection"" This reverts commit 40de0da.
… to test_connections.py
…ndsnet into tensor-wmin-and-wmax
- Removed MaxPool2DConnection - Added conditional checks for specific connections & update rules - wmin/wmax added to input connection due to WeightDependentPostPre rule not liking the default -inf/+inf values on the input layer
…ndsnet into tensor-wmin-and-wmax
|
@cearlUmass and @mahbodnr Well Done! |
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Outdated suggestions cannot be applied.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.
Added ability to use tensors for wmin/wmax on synaptic connections. Primary changes were the assignment of wmin and wmax as torch.Parameter's in the abstract connection class so they can always be interpreted as tensors (either of single or multiple values), and wrapping checks for -/+ inf in the wmin/wmax with an any() function. This occurred in both the Learning.py and Topology.py files.
Note: