Results
2
comments of
秦鹏
> 您好， > > 因为pytorch是按照名字来load权重的，dataparallel出来的名字可能不一样，你可以检查一下，应该前面有个models. > > 谢谢关注 你好，请问我出现这个错误，是怎么回事 if imgnet_pretrained: pretrained_state = torch.load(cfg.MODEL.PRETRAINED, map_location='cpu')['state_dict'] model_dict = model.state_dict() pretrained_state = {k: v for k, v in pretrained_state.items() if (k in...