-
Hi,
I am using the transR and WN18 data to train. Training is fineing. Then I am using the output .vec and the given test2id.txt given in the WN18 directory to make an inference from the data using…
-
Hi, I have failed to reproduce results of ComplEx on WN18RR and FB15K237 reported in ConvE paper. I use an implementation of myself and it can reproduce results of FB15K and WN18 correctly. Could you …
-
**Lighthouse Version**: 3.0.1
**Lighthouse Commit**: dfb6cc9d749f9855071202589dea40f110232631
**Chrome Version**: 67.0.3396.99
**Initial URL**: https://osmo.mobi/g/wn18
**Error Message**: FAILED_D…
GaMsh updated
6 years ago
-
I think the culprit is
```
c++ -pthread -std=c++0x -march=native -O3 -funroll-loops -c src/fasttext.cc
‘void fasttext::FastText::quantize(const fasttext::Args&)’: src/fasttext.cc:302:45: warning…
-
运行sh train_fb15k.sh会在model.py第168行 eval_result_queue.join() 卡住，但是运行sh train_wn18.sh.sh没有任何问题。人为ctrl+c结束会显示
Traceback (most recent call last):
File "main.py", line 44, in
main()
File "main…
-
-
I did manage to extract feature using the configuration file approach, and they are stored into two file `training_matrix.tsv` and `test_matrix.tsv`.
I've extracted a random observation from the `tra…
-
your data in three files train.txt, valid.txt and test.txt Each line is a triple, but not in the format like ubject_entity_id relation_id object_entity_id. How your program works with this data tha…
-
1. paper say use early stop but it seems the code just train 1000 epochs ?
2. paper say force L2 norm for DistMult and CompEx but I didn't see where is it ?
3. I don't think we should see the test r…
-
大神们是在服务器上跑的？我训练的wn18，跑了6个小时。求解，祝好。