nateraw / Lda2vec-Tensorflow

Tensorflow 1.5 implementation of Chris Moody's Lda2vec, adapted from @meereeum
MIT License
107 stars 40 forks source link

Issues in 'run_20_newgroups.py' when load_embed = False #55

Open dbl001 opened 5 years ago

dbl001 commented 5 years ago
  1. vocab_size does not get set with load_embed = False E.g.
    vocab_size = embed_matrix.shape[0] 
  2. utils.load_preprocessed_data() returns 6 parameters (not 7) when load_embed = False
    
    (idx_to_word, word_to_idx, freqs, pivot_ids,
    target_ids, doc_ids, **_embed_matrix_**) = utils.load_preprocessed_data(data_path, load_embed_matrix=load_embeds)
dbl001 commented 5 years ago

Perhaps:

vocab_size = embed_matrix.shape[0] if load_embeds else len(idx_to_word)