search

cog-imperial / OMLT

Represent trained machine learning models as Pyomo optimization formulations
Other
273 stars 58 forks source link

Use smaller relu NN for auto-thermal-reformer #45

Closed jalving closed 2 years ago

jalving commented 2 years ago

This should help the notebook tests pass by using a smaller neural network for the auto-thermal-reformer-relu.ipynb . Previously, the call to Cbc would sometimes time-out and cause the tests to fail.

codecov[bot] commented 2 years ago

Codecov Report

Merging #45 (2eac906) into main (c1e7194) will not change coverage. The diff coverage is n/a.

Impacted file tree graph

@@           Coverage Diff           @@
##             main      #45   +/-   ##
=======================================
  Coverage   91.14%   91.14%           
=======================================
  Files          24       24           
  Lines        1231     1231           
  Branches      186      186           
=======================================
  Hits         1122     1122           
  Misses         80       80           
  Partials       29       29

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update c1e7194...2eac906. Read the comment docs.

jalving commented 2 years ago

@rmisener: this should be okay to merge. I will update the other PRs to test with the smaller relu network.