bbox_loss missing during traing the pgd model on waymo dataset. #2069
Unanswered
hanssssssss
asked this question in
Q&A
Replies: 1 comment 1 reply
-
Please provide more details. You can create an issue. BTW, please check whether you calculate the loss in your model forward. |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I used config file
pgd_r101_fpn-head_dcn_16xb3_waymoD5-fov-mono3d.py
and during training, I found that I could not see the bbox_loss on the log file. But the bbox_loss is defined in the config file as:loss_cls=dict( type='mmdet.FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=1.0), loss_bbox=dict( type='mmdet.SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0), loss_dir=dict( type='mmdet.CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_centerness=dict( type='mmdet.CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), use_depth_classifier=True, depth_branch=(256, ), depth_range=(0, 50), depth_unit=10, division='uniform', depth_bins=6, pred_keypoints=True, weight_dim=1, loss_depth=dict( type='UncertainSmoothL1Loss', alpha=1.0, beta=3.0, loss_weight=1.0), loss_bbox2d=dict( type='mmdet.SmoothL1Loss', beta=1.0 / 9.0, loss_weight=0.0), loss_consistency=dict(type='mmdet.GIoULoss', loss_weight=0.0),
Beta Was this translation helpful? Give feedback.
All reactions