casperkaae / parmesan

Variational and semi-supervised neural network toppings for Lasagne
Other
208 stars 31 forks source link

Wrong gradients in NormalizingPlanarFlowLayer #50

Open Era-Dorta opened 6 years ago

Era-Dorta commented 6 years ago

If I understand correctly, equation 11 in the paper is computed here, where for a batch of 5 and with 3 features, h'(w^t + b) should have a shape of (5,) and w of (3,), thus psi should be a (5, 3), and psi_u (5,). However, in the current implementation psi is (5,) and psi_u is a scalar. So the solution would be the change the dot product for a element-wise product. Is that right or did I make a mistake?