OpenKE
OpenKE copied to clipboard
thunlp
An Open-Source Package for Knowledge Embedding (KE)
Hi, Thanks for this awesome toolkit! However, I am struggling to find a way to actually access and use the generated embeddings. In the available [pretrained embeddings](http://139.129.163.161/index/toolkits#pretrained-embeddings), binary files exist...
我目前的知识图谱实体在1500万个左右，在运用transE进行训练时显示oom错误，即使batch size设置为1，也会出现oom错误，请问怎么解决呢？ Traceback (most recent call last): File "train_transe_WN18_adv_sigmoidloss.py", line 52, in trainer.run() File "/ai-images/wjy/event_extraction/recommendation/OpenKE-PyTorch/openke/config/Trainer.py", line 93, in run loss = self.train_one_step(data) File "/ai-images/wjy/event_extraction/recommendation/OpenKE-PyTorch/openke/config/Trainer.py", line 52, in train_one_step loss.backward() File...
Hey guys, thanks für this great toolkit. Would it be possible to write a Python API so one could use it dirctly in a jupyter notebook? It would help if...
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 occupied...
An end-to-end script to convert conceptnet.io assertions to training dataset
Hi there. Thanks for introducing this useful tool! Due to the need for my research I have generalized the data loading part to allow for multiple data loaders in a...
Hello, for the training the TrainDataLoader uses a batch_y for the data sampling (which is then used for training), what is that and why is it needed? I get the...
我尝试采用https://github.com/yuyuz/MetaQA这个数据集里面的kb.txt(三元组（h,r,t）)和python代码构建: entity2id.txt relation2id.txt train2id.txt test2id.txt valid2id.txt这几个文件， 我发现kb.txt里面有重复的三元组，我将重复的三元组删除了并且也严格对应要求的(e1,e2,r)对格式进行了修改，而且采用'\t'进行分隔，但还是会报错：Segmentation fault，烦请各位前辈告诉我可能的原因，谢谢！
很感谢作者能够开源您的代码，在测试常规数据集后，将本人自己构建的数据集进行训练时出现了以下问题： Fatal glibc error: malloc assertion failure in sysmalloc: (old_top == initial_top (av) && old_size == 0) || ((unsigned long) (old_size) >= MINSIZE && prev_inuse (old_top) && ((unsigned long) old_end...
As my research project, I am trying to use OpenKE for loading Wikidata [truthy NT file](https://dumps.wikimedia.org/wikidatawiki/entities/) However, when I reach the following step in `openke/config/Trainer.py` file ``` if self.use_gpu: self.model.cuda()...
