search

tianzhi0549 / FCOS

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
https://arxiv.org/abs/1904.01355
Other
3.28k stars 630 forks source link

Problem about size mismatch. #65

Closed jsjs0827 closed 5 years ago

jsjs0827 commented 5 years ago

I try to run the demo/fcos_demo,but size mismatch occurs. I use the default setting in the fcos_demo,config-file:configs/fcos/fcos_R_50_FPN_1x.yaml; weights:FCOS_R_50_FPN_1x.pth. The difinite description is below: RuntimeError: Error(s) in loading state_dict for GeneralizedRCNN: size mismatch for rpn.head.cls_logits.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([15]). size mismatch for rpn.head.cls_logits.weight: copying a param with shape torch.Size([80, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([15, 256, 1, 1]). size mismatch for rpn.head.bbox_pred.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([60]). size mismatch for rpn.head.bbox_pred.weight: copying a param with shape torch.Size([4, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([60, 256, 1, 1]). What should I do?

tianzhi0549 commented 5 years ago

@jsjs0827 Did you change the code or any settings?

jsjs0827 commented 5 years ago

No. Can you give any suggestion？