Pytorch_Retinaface icon indicating copy to clipboard operation
Pytorch_Retinaface copied to clipboard

Published 20 hours ago • verified publisher icon biubug6

When I want to use mobilenetX0.25_pretrain.tar as a backbone, I got the following error. What did I do wrong?

Open yeahyeahye opened this issue 3 years ago • 0 comments

RuntimeError: Error(s) in loading state_dict for MobileNetV1: size mismatch for stage1.0.0.weight: copying a param with shape torch.Size([8, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([8, 3, 2, 2]).

yeahyeahye avatar Jun 29 '21 09:06 yeahyeahye