How to solve this error missing_keys=[]?

IncompatibleKeys(missing_keys=[], unexpected_keys=[])

When I tried to use IBN-net as an feature extractor, I met an error.

class LargeModel(nn.Module):
    def __init__(self, pretrain=True):
        super(LargeModel, self).__init__()

        # define ibn_model and initilize it with pretrained model.
        IBN_model_name = 'resnet50_ibn_a.pth.tar'
        IBN_model = resnet50_ibn_a(pretrained=False)
        pretrained_model_weight = torch.load(IBN_model_name)['state_dict']
        new_state_dict = OrderedDict()
        for k, v in pretrained_model_weight.items():
            name = k[7:] # remove `module.`
            new_state_dict[name] = v
     #   for k, v in new_state_dict.items():
     #       print(k)
     #   print('----------')
     #   for k in IBN_model.state_dict().keys():
     #       print(k)

        self.ibn_res50 = IBN_model.load_state_dict(new_state_dict)
         # Define Extra layers and initilize them with uniform distribution

When I try to print self.ibn_res50, it gives such error.
In fact, when I try to print new_state_dict and IBN_model.state_dict().keys(), both of them return the same keys.

This is not an error, since no incompatible keys were found.
Since this message was quite misleading, it was removed already and you shouldn’t see it in the current stable release (1.3.1).