wencolani / itere Goto Github PK
View Code? Open in Web Editor NEWIteratively Learning Embeddings and Rules for Knowledge Graph Reasoning. (WWW'19)
Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning. (WWW'19)
Hi Authors,
Have you considered experimenting with the original non sparse versions of the dataset? I tried to run it but don't know how to generate the axioms (Is the code for that present ?).
The axioms provided for the sparse versions should work for the original versions right ?. Because only test and valid sets are changed in the sparse version.
Hi Authors,
When running the main.py file on WN18RR-sparse dataset, I found an error. But it works well on other datasets without any similar problems.
Traceback (most recent call last):
File "main.py", line 94, in
main()
File "main.py", line 85, in main
experiment.train()
File "/home/user03/model/IterE/experiment.py", line 80, in train
self.test('test', num_test=test_num)
File "/home/user03/model/IterE/experiment.py", line 116, in test
self.test_triples, self.test_triples_org = self.generate_test_triples_batch(dataset,batch,num_test)
File "/home/user03/model/IterE/experiment.py", line 445, in generate_test_triples_batch
test_triple_replace = self.replace_test_triple(test_triple_ids)
File "/home/user03/model/IterE/experiment.py", line 451, in replace_test_triple
replace_head_rt = input_triples[:, 1:]
IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed
I had tried to correct it a few times,but it didn't work. Can you advise me how to solve this error?
Thank you!
Hi, could you please tell me why you filter the axiom with too many entailments? Thank you.
Traceback (most recent call last):
File "/Users/apple/Downloads/IterE-master/main.py", line 94, in
main()
File "/Users/apple/Downloads/IterE-master/main.py", line 85, in main
experiment.train()
File "/Users/apple/Downloads/IterE-master/experiment.py", line 88, in train
axioms_probability = self.update_axiom()
File "/Users/apple/Downloads/IterE-master/experiment.py", line 429, in update_axiom
with open('./save_axiom_prob/axiom_prob.pickle', 'wb') as f: pickle.dump(axiom_pro, f, pickle.HIGHEST_PROTOCOL)
FileNotFoundError: [Errno 2] No such file or directory: './save_axiom_prob/axiom_prob.pickle'
I run it but
Process Process-3:
Process Process-2:
Process Process-1:
Traceback (most recent call last):
Traceback (most recent call last):
Traceback (most recent call last):
File "/Users/apple/.conda/envs/IterE-master/lib/python3.6/multiprocessing/process.py", line 258, in _bootstrap
self.run()
File "/Users/apple/.conda/envs/IterE-master/lib/python3.6/multiprocessing/process.py", line 93, in run
self._target(*self._args, **self._kwargs)
File "/Users/apple/Downloads/IterE-master/data.py", line 892, in negative_triple_generator
if dat == None:
File "/Users/apple/.conda/envs/IterE-master/lib/python3.6/multiprocessing/process.py", line 258, in _bootstrap
self.run()
File "/Users/apple/.conda/envs/IterE-master/lib/python3.6/multiprocessing/process.py", line 93, in run
self._target(*self._args, **self._kwargs)
File "/Users/apple/.conda/envs/IterE-master/lib/python3.6/multiprocessing/process.py", line 258, in _bootstrap
self.run()
File "/Users/apple/Downloads/IterE-master/data.py", line 892, in negative_triple_generator
if dat == None:
File "/Users/apple/.conda/envs/IterE-master/lib/python3.6/multiprocessing/process.py", line 93, in run
self._target(*self._args, **self._kwargs)
File "/Users/apple/Downloads/IterE-master/data.py", line 892, in negative_triple_generator
if dat == None:
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
Dear Authors,
I found these error when executing IterE in my gpu machine:
self.pos_triples = tf.placeholder(tf.int32, [None, 3])
AttributeError: module 'tensorflow' has no attribute 'placeholder'
Can you advise me how to solve this error? was it because the version of tensorflow that IterE used different with the version of tensorflow in my gpu machine? If it was the case, I would like to ask about what version of tensorflow that IterE used.
Thank you
Hi the authors of IterE,
I found an error when I run IterE in my machine. This is the error message:
File "/nobackup/users/r01krw16/IterE/data.py", line 125, in _read_id ent2id_f = open(ent2id_file, 'r')
FileNotFoundError: [Errno 2] No such file or directory: './datasets/FB15k-237-sparse/entity2id.txt'
When I check data.py, I also found out that beside entity2id.txt, you should also provide relation2id.txt in this github.
Best Regards.
Dear Authors,
I found these errors when running IterE (the main.py file) on FB15k-237-sparse dataset.
Traceback (most recent call last):
File "main.py", line 93, in
main()
File "main.py", line 66, in main
inject_triple_percent = option.inject_triple_percent)
File "/uoa/scratch/users/r01krw16/IterE/data.py", line 58, in init
self.train_ids = self._triple2id(self.train_triples)
File "/uoa/scratch/users/r01krw16/IterE/data.py", line 143, in _triple2id
for (h,r,t) in triples]
File "/uoa/scratch/users/r01krw16/IterE/data.py", line 143, in
for (h,r,t) in triples]
KeyError: '/m/06cx9'
Can you advise me how to solve this problem? Thank you.
Please provide more detailed README, such as tensorflow version and python environment. Thank you.
hi,I'm confused about the function 'split_embedding', what does it do?thanks~
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.