Open saminheydarian97 opened 1 year ago
It seems different model structure in downsample layers. The reason can be different timm package like https://github.com/layumi/Person_reID_baseline_pytorch/issues/334, which updates swin model.
pip install git+https://github.com/rwightman/pytorch-image-models.git
I suggest you may consider to re-train your model under the same environment. It usually works.
Hi. I used the ft_net_swin for loading the model. When I run my code in my device there is no problem but in the kaggle I got this error.