search

omarsayed7 / Deep-Emotion

Facial Expression Recognition Using Attentional Convolutional Network, Pytorch implementation
249 stars 73 forks source link

Why the loss function is not same with paper said? #14

Open AlexFEIII opened 2 years ago

AlexFEIII commented 2 years ago

hello, I'm a student who is learning AI. I was download your code, but I have a problem about this code, The paper saids "The loss function in this work is simply the summation of two terms, the classification loss(cross-entropy), and the regularization term(which is l2 norm of the weights in the last two fully-connected layers)" In the main.py, I just see "the classification loss". Is there any particular reason for this?

finally, thank you for your code contributions

hnhoangdz commented 2 years ago

l2 norm is the loss function, it is a regularization technique. in this paper, the author wanted to applied l2 norm for only last fcn layers