Sync BatchNorm costs lots of time and cause code unworkable

[ppbangKGT]

Hi, thanks for your nice work!
When I run your code, there met a problem.
Because my device is unable to connect to the internet, I download the resnet50 pth pretrained on ImageNet instead of using the mm-pretrain model. This means I change the encoder config init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50') to init_cfg=dict(type='Pretrained', checkpoint='/data1/pbw/LATR-main/resnet50-19c8e357.pth')
By doing so, I successfully run the code. But it stops at operation "Convert model with Sync BatchNorm", and cannot go on. I have taken a screenshot as follows.

Could you give me some advice? Thanks for your time.

[zjulabwjt]

Hi, thanks for your nice work! When I run your code, there met a problem. Because my device is unable to connect to the internet, I download the resnet50 pth pretrained on ImageNet instead of using the mm-pretrain model. This means I change the encoder config init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50') to init_cfg=dict(type='Pretrained', checkpoint='/data1/pbw/LATR-main/resnet50-19c8e357.pth') By doing so, I successfully run the code. But it stops at operation "Convert model with Sync BatchNorm", and cannot go on. I have taken a screenshot as follows. Could you give me some advice? Thanks for your time.

have you solved this problem?