Skip to content

Conversation

@lenianiva
Copy link

This fixes a bug where during backpropagation the size of an array e.g. (1, 1, 0) does not match the size of the gradient e.g. (4, 1, 0). The error only happens for zero-sized arrays.

See an example here: JuliaGraphs/GraphNeuralNetworks.jl#638

@codecov
Copy link

codecov bot commented Jan 19, 2026

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 93.50%. Comparing base (004e43e) to head (8a5c3e9).

Additional details and impacted files
@@           Coverage Diff           @@
##             main     #702   +/-   ##
=======================================
  Coverage   93.49%   93.50%           
=======================================
  Files          15       15           
  Lines         999     1000    +1     
=======================================
+ Hits          934      935    +1     
  Misses         65       65           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

@lenianiva lenianiva changed the title fix: Allow arbitrary reshape if array is zero sized fix: Allow arbitrary reshape in projection if array is zero sized Jan 19, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant