Chen Hao

I find there is no softmax function when I should get the distribution of prediction. ----------------- wrapper.py def mlm_train_step(self, labeled_batch: Dict[str, torch.Tensor], unlabeled_batch: Optional[Dict[str, torch.Tensor]] = None, lm_training: bool =...

您好，因为README里的安装DGL的命令有问题 所以我安装DGL的命令改成这个了 conda install -c dglteam/label/cu102 dgl 但是最后出现了错误 AttributeError: Can't get attribute 'DGLHeteroGraph' on 这个DGL库是有什么版本要求吗