facebookresearch / poincare-embeddings

PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"
Other
1.68k stars 231 forks source link

Unable to use my own data #17

Closed NooneBug closed 5 years ago

NooneBug commented 6 years ago

I'm trying to use my own data in tsv format but I have a problem:

The console returns me this message:

"./poincare-embeddings/model.py", line 156, in init assert len(objects) == nents, 'Number of objects do no match' AssertionError: Number of objects do no match

I'd like to know what is the meaning of this assertion . Even because if I put a comment on the line, everything works.

Thanks

carricky commented 5 years ago

same problem here

lematt1991 commented 5 years ago

This should be resolved now. Please re-open a new task if you have issues with using your own data again.

Clarioooo commented 5 months ago

Which file is model.py? Has it been renamed embed.py? I want to use the code on another dataset, but I just changed the file 'mammals_filter.txt' opened in transitive_closure.py, but it seems that the generated data is still mammals. Am I running it wrong?

image