Closed creater-zq closed 2 years ago
It's normal to print this error because of the difference between the backbones of pre-training and downstream tasks.
However, this is just a warning as the strict=False
:
https://github.com/SwinTransformer/Swin-Transformer-Object-Detection/blob/a90acdda2156c93a447e16a2fd8befc63bd534de/mmcv_custom/checkpoint.py#L97-L106
哦哦哦,也就是不用管,直接train就完事了
您好!我使用
upernet_uniformer
做语义分割,只使用了一个GPU。uniformer_base_in1k.pth
,加载时出现如下错误:missing keys in source state_dict: norm1.weight, norm1.bias, norm2.weight, norm2.bias, norm3.weight, norm3.bias, norm4.weight, norm4.bias
norm_cfg
进行修改。pretrained_path
: