Conversation
torch has supported a native bool dtype since 1.2 (2019), but Nodes.s and its downstream consumers were still allocated as uint8. This meant spike checks relied on comparison hacks like (s > 0) instead of direct boolean semantics, and precluded using logical ops (&, |, ~, .any(), .all()) directly on spike tensors. Changes: - Nodes.__init__ / reset_state_variables: self.s now allocated with dtype=torch.bool - Learning rules (learning.py): explicit .float() casts added where spikes are used in arithmetic weight updates - Encoders (encoding.py): output dtype aligned to bool at the spike-train boundary Closes BindsNET#318
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
torch has supported a native bool dtype since 1.2 (2019), but Nodes.s and its downstream consumers were still allocated as uint8. This meant spike checks relied on comparison hacks like (s > 0) instead of direct boolean semantics, and precluded using logical ops (&, |, ~, .any(), .all()) directly on spike tensors.
Changes:
Closes #318