Bigger Lambda

Did you try doing clearState() before using model:float(). It clears the intermediary states in the model (not needed for prediction)

@cjnolet I think just the proposals without the postprocessing and tinkering with box dimensions leads to poor recall (see image below). @ankush-me can you confirm? 

Can you share a c# sample? I am having problems with emulating the java code to c#

I can confirm that it is possible to mix `optim` with wrapped `nn` modules. Errors that you hit might be features that `autograd` does not support.