Engine

Results 23 comments of Engine

> 同样参数在kyzhouhzau/BERT-NE没有这个现象,在这里也有X,请问怎么解决的啊 求问,在跑kyzhouhza/BERT-NE的时候出现下面这个错误 absl.flags._exceptions.UnparsedFlagAccessError: Trying to access flag --do_train before flags were parsed 您遇到过吗,我是直接放好模型后进行训练的

Same with you, have you deal with this problem? >>> import graphvite Traceback (most recent call last): File "", line 1, in File "/home/lyj/anaconda3/envs/graphvite3/lib/python3.8/site-packages/graphvite/__init__.py", line 30, in os.path.realpath(os.path.join(os.environ["PREFIX"], "lib")), File...

> Has anyone solved this issue? I have been struggling with it for many days. me too~

> 你好@zheng-da @asaluja 我有相同的用例,即对带有头/尾实体类型限制的负样本进行采样。正如您所建议的,我将种子边缘设置为属于特定边缘类型/关系的边缘。但是,`EvalSampler`(或`dgl.contrib.sampling.EdgeSampler`)通过从所有实体(包括头和尾)集合中随机采样节点的头或尾位置来破坏边缘。我希望头部是种子边缘中所有可能的头部之一(对于尾部损坏也是如此)。有什么建议可以实现吗?提前致谢。 Hello, I think you have learned the code in detail, so I want to ask you. On the paper, I see when sampling, the pos_g has...

修改.unicode,编码方式就行啦

> > 解决了,用作者的data.py生成文件即可 > > 您好,我可以请教一下您如何用自己的数据生成word2id吗,在data.py中需要修改什么数据呢 您好,是用data.py里的哪个函数呀,需要传什么参数!感激不尽

> > 我使用自己的数据集,也重新训练了Word2id.pkl,数据集都是用tab隔开的,但是在python main.py --model=train 的时候这样报错 > > 您好,可以请教一下您怎么生成自己的向量吗,需要修改代码中的哪些地方呢 +1, 同问如何生成Word2id.pkl

> Some variables can be deleted to optimize GPU memory use. For example, in the implementation of TransR, since the parameters pretrained on TransE are set to TransR, the tensors...