Closed wujiyoung closed 5 years ago
This may caused by different versions of PyTorch. The num_batches_tracked
is included in newer PyTorch versions.
You can set net.load_state_dict(..., strict=False)
to avoid the error.
This may caused by different versions of PyTorch. The
num_batches_tracked
is included in newer PyTorch versions.You can set
net.load_state_dict(..., strict=False)
to avoid the error.
you are right, it worked, thank you.
Error happened when loading state_dict from the pretrained model (download from google drive) for SiamFC.