Using different loss functions for different outputs simultaneously Keras?

تعرفه تبلیغات در سایت

آرشیو مطالب

امکانات وب

Vote count: 0

I'm trying to make a network that outputs a depth map, and semantic segmentation data separately.

In order to train the network, I'd like to use categorical cross entropy for the segmentation branch, and mean squared error for the branch that outputs the depth map.

I couldn't find any info on implementing the two loss functions for each branches in the Keras documentation for the Functional API.

Is it possible for me to use these loss functions simultaneously during training, or would it be better for me to train the different branches separately?

asked 1 min ago
Kemal Ficici

نویسنده : استخدام کار بازدید : 0 تاريخ : شنبه 11 فروردين 1397 ساعت: 10:05
برچسب‌ها :



نام کاربري :
رمز عبور :