Segmentation fault

[LoneChristmas]

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！

[LoneChristmas]

抱歉再来打扰一下，我执行train_rotate_WN18RR_adv.py(openke自带的rotate例子)的时候会出现：Finish initializing...
0%| | 0/1500 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/mnt/d/learning/kgqa/KGQA-master/OpenKE/train_rotate.py", line 47, in
trainer.run()
File "/mnt/d/learning/kgqa/KGQA-master/OpenKE/openke/config/Trainer.py", line 94, in run
loss = self.train_one_step(data)
File "/mnt/d/learning/kgqa/KGQA-master/OpenKE/openke/config/Trainer.py", line 53, in train_one_step
loss.backward()
File "/home/stone/.local/lib/python3.10/site-packages/torch/_tensor.py", line 487, in backward
torch.autograd.backward(
File "/home/stone/.local/lib/python3.10/site-packages/torch/autograd/init.py", line 200, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
RuntimeError: CUDA error: unknown error
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
这样的情况，想问一下这个是由于cuda和pytorch版本对不上的问题吗？我用的是wsl+ubuntu，但是运行其他模型的训练例子代码都没什么问题，想请教一下有没有什么解决的思路。

[hp962183985]

我也有segmentation fault的错误，请问你是怎么解决的？存储格式也是按照examples里数据集改的

[Aipura]

train_dataloader = TrainDataLoader(
in_path = "./benchmarks/MetaQA/TransE/",
nbatches = 100,
threads = 8,
sampling_mode = "normal",
bern_flag = 1,
filter_flag = 1,
neg_ent = 25,
neg_rel = 0)

add "/" at the end of in_path line, and then solved the Segmentation fault problem.

[rascalvain]

Aipura‘s suggestion is so helpful.Thank you so much！

[galaxywwww]

请问怎么解决Segmentation fault错误呢

[galaxywwww]

我在in_path后面加了/还是报错

[Lightningnemo]

说一下我的情况，我首次使用openke-pytorch，报错segmentation fault，发现这个版本的代码教程在https://github.com/thunlp/OpenKE/tree/OpenKE-PyTorch，按照这里面的流程，需要先执行cp examples/train_transe_FB15K237.py ./这一步，然后就不会报错了，应该还是路径的问题。