Open study1994 opened 2 years ago
It looks normal if it is at the beginning of the training, Why did you say drop in losses is abnormal?
At the end of training, loss is also very big,The following is a log comparison of two different settings More detailed logs are here:链接:https://pan.baidu.com/s/12t6i7NxWQ56RKn8h91qz1g?pwd=lqo4 提取码:lqo4
Hi, I check the code and think the potential reason might be the matching cost BBoxBEVL1Cost
used in our label assigner:
https://github.com/XuyangBai/TransFusion/blob/53370467c1b88f163cbe7b7300a1f588a6761e35/mmdet3d/core/bbox/assigners/hungarian_assigner.py#L25-L36
It calculates the error between prediction bbox and the ground truth where the box size is normalized by the pc_range
, so when x,y ranges are inconsistent, their importance will also be different in label assignment. That might leads to a noisy label assignment result because the network tends to choose a prediction with better y
prediction as the positive while somewhat ignoring the x
prediction.
A quick way to verify this idea is to set the range to [-70.4, -70.4, -2.0, 70.4, 70.4, 4.0]
. An alternative is to use BBoxL1Cost
instead, which uses the absolute error between predictions and ground truth. But you need to tune with the weight for reg_cost
, I have used this one but do not remember exactly the specific value.
Hope that helps.
I'll try it,thank you!
My data only has forward radar scan data, similiar with kitti dataset,so there is a big difference between point range and waymo, especially in the dimension of the x-axis, how should this be modified?
My data only has forward radar scan data, similiar with kitti dataset,so there is a big difference between point range and waymo, especially in the dimension of the x-axis, how should this be modified?
any solutions?
I am trying to train transfusion-L and transfusion-LC on my data,when i train like this
drop in losses is abnormal like this training results do not converge but mmdetection3d can do well while point_cloud_range = [-51.2, -51.2, -2.0, 51.2, 51.2, 4.0] in tranfusion .it alse can do well. I can't find a bug in the code。 Can you give me some advice?