SciML / OperatorLearning.jl

No need to train, he's a smooth operator
https://operatorlearning.sciml.ai/dev
MIT License
44 stars 8 forks source link

Tests for DeepONet layer #36

Open ba2tro opened 2 years ago

ba2tro commented 2 years ago

Added tests for forward pass, gradient and training

pzimbrod commented 2 years ago

Just noticed that one commit includes the dependency issue discussed in #35. We should adapt that here as well.

codecov[bot] commented 2 years ago

Codecov Report

Merging #36 (2bf6aaa) into master (7e9f9c2) will increase coverage by 4.10%. The diff coverage is n/a.

:exclamation: Current head 2bf6aaa differs from pull request most recent head ea38a5f. Consider uploading reports for the commit ea38a5f to get more accurate results

@@            Coverage Diff             @@
##           master      #36      +/-   ##
==========================================
+ Coverage   41.09%   45.20%   +4.10%     
==========================================
  Files           6        6              
  Lines          73       73              
==========================================
+ Hits           30       33       +3     
+ Misses         43       40       -3     
Impacted Files Coverage Δ
src/DeepONet.jl 60.00% <0.00%> (+20.00%) :arrow_up:

:mega: Codecov can now indicate which changes are the most critical in Pull Requests. Learn more