n2v - loadEmbedding IndexError, python 2.7

[dmpierre]

Hi Palash,

I think the loadEmbedding is encountering some issues, though I train the graph smoothly. I anyway can load the tempGraph.emb file but you may want to look at this traceback :)

Traceback (most recent call last): File "train.py", line 81, in <module> n2v_model = model.train_n2v_model(G, params) File "train.py", line 32, in train_n2v_model embedding.learn_embedding(g) File "/home/pdaixmor/.virtualenvs/word_embeddings/lib/python2.7/site-packages/gem-1.0.0-py2.7.egg/gem/embedding/node2vec.py", line 84, in learn_embedding self._X = graph_util.loadEmbedding('tempGraph.emb') File "/home/pdaixmor/.virtualenvs/word_embeddings/lib/python2.7/site-packages/gem-1.0.0-py2.7.egg/gem/utils/graph_util.py", line 170, in loadEmbedding X[int(emb[0]), :] = emb_fl IndexError: index 6256 is out of bounds for axis 0 with size 6224

[palash1992]

The nodes need to be contiguous. Do you think that can be the issue in your setting?

[dmpierre]

Hey Palash, sorry for the late reply.

Yes that was the issue. Maybe a dict-like way for accessing the embeddings could be more appropriate for such a case - such as in gensim. What do you think? :)

[palash1992]

Yes I agree. I am currently working on an extension of the library. Perhaps once I am done with that I can make this change for both of them.

[Anjs04]

@dmpierre How did you load the embeddings without using loadEmbeddings()?

[dmpierre]

Hi :)

Just comment out line 84 in node2vec.py:
self._X = graph_util.loadEmbedding('tempGraph.emb')

Then you can write your own kind of loadEmbedding function that best suits your needs.