Skip to content

Load pretrained word embeddings (word2vec, glove format) into torch.FloatTensor for PyTorch

Notifications You must be signed in to change notification settings

iamalbert/pytorch-wordemb

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

pytorch-wordemb

Load pretrained word embeddings (word2vec, glove format) into torch.FloatTensor for PyTorch

Install

PyTorch required.

pip install torchwordemb

Usage

import torch
import torchwordemb

torchwordemb.load_word2vec_bin(path)

read word2vec binary-format model from path.

returns (vocab, vec)

  • vocab is a dict mapping a word to its index.
  • vec is a torch.FloatTensor of size V x D, where V is the vocabulary size and D is the dimension of word2vec.
vocab, vec = torchwordemb.load_word2vec_bin("/path/to/word2vec/model.bin")
print(vec.size())
print(vec[ w2v.vocab["apple"] ] )

torchwordemb.load_word2vec_text(path)

read word2vec text-format model from path.

torchwordemb.load_glove_text(path)

read GloVe text-format model from path.

About

Load pretrained word embeddings (word2vec, glove format) into torch.FloatTensor for PyTorch

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published