-
### What is your question
Would it be possible to get some insights/info about the benchmarks discussed in #417 and how the different datasets/settings were affected?
I have noticed some big runti…
-
I run the transE directly
And then I got this error:
Input Files path:
Input Files path:
Process finished with exit code 139 (interrupted by signal 11: SIGSEGV)
The data path is already in the …
-
D:\anaconda3\envs\pytorch\python.exe E:/pycharmProjects/OpenKE-OpenKE-PyTorch/examples/train_transe_WN18_adv_sigmoidloss.py
Traceback (most recent call last):
File "E:/pycharmProjects/OpenKE-OpenK…
-
I just tried the hyper parameters from the FB15K example in the example file train_transe.py (PyTorch Old) which didn't work very well.
Does anyone know the optimal hyper parameters for the new Op…
-
Why does only the RGCN **WN18** experiment use the `schlichtkrull` sampler and the **FB15k** dosn't?
-
## ❓ Questions and Help
Hi, I have two small questions regarding to the implementation of Pytorch RGCN.
1. It seems that in the `link_prediction.py` file, the `train_data` is used to build the …
-
Hi, how do you split the knowledge graph into train/valid/test? I am confused about how to make all entities appearing in the training set.
SRL94 updated
3 years ago
-
## 🐛 Bug
The results of the training process differ from those of the paper.
## To Reproduce
Steps to reproduce the behavior:
1. Train and evaluate model for the WN18 Dataset
2. Train a…
-
Thank you for developing great work, RotatE. I'm really interested in your research.
1. I ran your program as the following, but I found that there is a bug "RuntimeError: CUDA out of memory". How…
-
At first this is a amazing code work! and after running the code, the code showed the error that the 'WN18_torch_TransE_entity_50dim_batch4800' file can not be found, and i cannot find it in the whol…