Tracyummy

您好，我看到在loss.py文件中，是对预设的所有anchors分配IoU最大的gt（torch.max函数），这样会不会不太合理，虽然说预测框anchor数量很多，大概率不会有gt没有分配到anchor。 我觉得反过来给每个anno按照IoU分配最大的anchor是不是会更合理一些

did point loss contributes to total loss?

1

I found `loss_dict_reduced_scaled = {k: v * weight_dict[k] for k, v in loss_dict_reduced.items() if k in weight_dict}` the key in weight_dict and loss_dict_reduced is not consistent with each other. one...

How to solve it？PLZ！！！

2

KeyError: 'def_b1_hila is not in the backbone registry'  

plz public the pretrained weights

3

could you share the pretrained weights in your paper to help reproduce the result.