search

cog-imperial / OMLT

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

Notebooks for the auto-thermal-reformer example #31

Closed carldlaird closed 2 years ago

carldlaird commented 2 years ago

Included two notebooks for the auto-thermal reformer example. One that uses Sigmoid and one the uses Relu

codecov[bot] commented 2 years ago

Codecov Report

Merging #31 (ff47747) into main (e466993) will not change coverage. The diff coverage is n/a.

Impacted file tree graph

@@           Coverage Diff           @@
##             main      #31   +/-   ##
=======================================
  Coverage   88.79%   88.79%           
=======================================
  Files          23       23           
  Lines        1071     1071           
  Branches      160      160           
=======================================
  Hits          951      951           
  Misses         98       98           
  Partials       22       22

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 e466993...ff47747. Read the comment docs.

rmisener commented 2 years ago

Tiny typographic issue (mostly to prove that I have read these very nice notebooks!): in auto-thermal-reformer.ipynb, change the "ReLU" in the introductory discussion ("In this example, we will train a ReLU model ...") to "In this example, we will train a model with sigmoid activation functions ...").

Additionally, is it possible to solve auto-thermal-reformer-relu.ipynb with CBC? The way @fracek set-up the notebooks to get automagically tested needs open source solvers.