-
Nice work! However, I found that the relation embedding file in neural_adj folder is too big to load. Even for FB15K-237, the file size is over 50GB. The GPU memory is always out of memory for subsequ…
-
Hi, i'm having a problem while training fb15k237 using default parameters. Any suggestions? thanks
###
Can't pickle local object 'get_linear_schedule_with_warmup..lr_lambda'
File "/Relphormer/ma…
-
Hello, I am interested in your paper. I would like to ask you about the approximate time for this code to run in each task. How much GPU memory is consumed?
-
### Describe the bug
I am trying to reproduce the LiteralE results mentioned in the [original paper](https://arxiv.org/abs/1802.00934), starting from _DistMult+LiteralE-glin_. The hyperparameter valu…
-
hello，I try to reproduce the results on the paper. As for the WN18RR，I got the similar results. But the precision and recall of FB15K, I get diffident results.
. Can you please help me …
-
Below is my code
```python
import torch
from torchdrug import core, datasets, tasks, models
from torchdrug.models import RotatE
import matplotlib
matplotlib.use('TkAgg')
import matplotlib.pyp…
-
Hello, I'm new to machine learning, I'm trying to train RGCN with my own dataset, but I don't know how to create 'train_mask" .
In RGCN/link.py, when I print (g.edata) of FB15k237Dataset, the outp…
-
Hi,
I found the Hits@10 of RotatE in FB15k237 **(0.553)** is higher than original paper **(0.533)**. And others are same.
Is this a recording error or did you improve the performance of RotatE…
-
按照readme中显示流程，对fb15k-237预训练(pretrain_fb15k-237-image.sh)，在第五个epoch就达到了hit@1=0.99，用此模型进行训练(fb15k-237-image.sh)，得到的结果hit10为0.504，请问是否是我的训练参数没有调整正确呢，或者是训练过程不对呢