How tensorflow graph regularization (NSL) affects triplet semihard loss (TFA)

Question

I want to train a binary target deep neural network model using nsl.keras.GraphRegularization as described in this tutorial . My model has a triplet semihard loss in an intermediate dense layer which should not be "graph regularized".

From the nsl.keras.GraphRegularization definition on Github:

Incorporates graph regularization into the loss of base_model .

Graph regularization is done on the logits layer and only during training.

It means that the intermediate triplet semihard loss will not be affected by this regularization?

Answer 1

Yes, that's right. Graph regularization will only be applied on the outputs of base_model . If your base_model uses triplet semihard loss in another layer, that loss should remain unaffected and preserved. If that's the not the case, please file a bug athttps://github.com/tensorflow/neural-structured-learning/issues .