cemanil / LNets

Lipschitz Neural Networks described in "Sorting Out Lipschitz Function Approximation" (ICML 2019).
55 stars 19 forks source link

Lipschitz Constant #6

Open wollschlager opened 4 years ago

wollschlager commented 4 years ago

When I use the hardcoded LeNet structure and train it with the provided config (lenet_bjorck) file I am not achieving the Lipschitz Constant of 1 even after orthonomal finetuning (some of the singular values are a little over 1).

Should I do anything different?

When I try to use the fully_convolutional_2d architecture, what should the "l_correction_constant" be to calculate the "l_constant_per_layer"?