Add gemm nodes to onnx reader

cog-imperial / OMLT

Represent trained machine learning models as Pyomo optimization formulations

Other

262 stars 57 forks source link

Add gemm nodes to onnx reader #2

Closed fracek closed 2 years ago

fracek commented 2 years ago

I added gemm (aAB + bC, where a, b are scalars, and A B C are tensors) nodes to the onnx reader because that's what the pytorch exporter uses for fully connected layers.

I also changed the reader to include scaling objects and input bounds parameters.

fracek commented 2 years ago

@jalving Can you take a look at this and merge it please?