Skip to content

PyTorch implementation of the Word2Vec (Skip-Gram Model) and visualizing the trained embeddings using TSNE

Notifications You must be signed in to change notification settings

n0obcoder/Skip-Gram-Model-PyTorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Skip-Gram-Model-PyTorch

PyTorch implementation of the word2vec (skip-gram model) and visualization of the trained embeddings using TSNE !

2D representaion of some of the trained word embeddings

My TensorFlow implemntation of Skip-Gram Model can be found here.

Requirements

  • torch >= 1.4
  • numpy >= 1.18
  • matplotlib
  • tqdm
  • nltk
  • gensim

Training

python main.py

Visualizing real-time training loss in Tensorboard

tensorboard --logdir <PATH_TO_TENSORBOARD_EVENTS_FILE>

NOTE: By default, PATH_TO_TENSORBOARD_EVENTS_FILE is set to SUMMARY_DIR in config.py

Testing

python test.py

Inference

war india crime guitar movies desert physics religion football computer
fight europe despite band movie region theory religious team program
battle central help play series along mathematics christian win systems
army western seek record show western mathematical regard sport available
force indian challenge piece film southern study tradition club design
ally part fail star feature plain science christianity league information

Blog-Post

Check out my blog post on word2vec here.

About

PyTorch implementation of the Word2Vec (Skip-Gram Model) and visualizing the trained embeddings using TSNE

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages