New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Location Decoder loss #3

Closed

hust-nj opened this issue Dec 20, 2021 · 0 comments

hust-nj commented Dec 20, 2021

Panoptic-SegFormer/easymd/models/panformer/panformer_head.py

Lines 360 to 364 in e604ef8

    
           # if the location decoder codntains L layers, we compute the losses of the first L-1 layers 
        
           losses_cls, losses_bbox, losses_iou = multi_apply( 
        
               self.loss_single, all_cls_scores[:-1], all_bbox_preds[:-1], 
        
               all_gt_bboxes_list, all_gt_labels_list, img_metas_list, 
        
               all_gt_bboxes_ignore_list)

Why does the location decoder only compute the losses of the first L-1 layers not the whole L layers?

The text was updated successfully, but these errors were encountered:

hust-nj closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment