search

cog-imperial / OMLT

Represent trained machine learning models as Pyomo optimization formulations
Other
281 stars 59 forks source link

MaxPool layers: add support for non-increasing activation functions on preceding convolutional layer #154

Closed jezsadler closed 5 months ago

jezsadler commented 5 months ago

Per the TODO note on line 273 of full_space.py:

# TODO: add support for non-increasing activation functions on preceding
# convolutional layer
rmisener commented 5 months ago

We don't support non-increasing activation functions and don't have a plan to at this point.