Question about the Custom loss function on Recognition (like ViT model)

taoyang1122 / adapt-image-models

[ICLR'23] AIM: Adapting Image Models for Efficient Video Action Recognition

Apache License 2.0

278 stars 21 forks source link

Question about the Custom loss function on Recognition (like ViT model) #26

Open andrewwang0612 opened 1 year ago

andrewwang0612 commented 1 year ago

Hello，Thanks for the amazing project!

I would like to ask how to configure the loss function in the training of a recognition model such as ViT. Specifically, I have seen that for tasks like object detection, the loss function is set as "loss_bbox." However, I am unsure of how to set the loss configuration for recognition tasks.

Thanks for helping!

taoyang1122 commented 1 year ago

Hi, the loss function really depends on you task. For example, in classification, people usually use cross_entroy loss. And as you mentioned, in object detection, they have both classification and regression losses. You could check different works and follow their settings.