search

manigalati / usad

Other
206 stars 58 forks source link

Question about the Loss functions (L2 norm?) #9

Closed htakatsuka closed 1 year ago

htakatsuka commented 2 years ago

Hello. May I ask about the loss functions inside the training_step? The paper states that ||x||2 denotes L2 Norm. As I understand, L2 norm is the "square root of sum of squares of elements inside x". However, the loss of the training step seems to be using MSE (mean((batch-w3)**2) etc). Was this a change from the paper or did I not understand L2 norm correctly? Thanks in advance!

pzpzpzp commented 1 year ago

Hello, have you solved this problem? Is there any error in the loss function defined in usad.py?

htakatsuka commented 1 year ago

This issue was only a question. No one has answered me until now so I will close this. Thank you.