tensormsa icon indicating copy to clipboard operation
tensormsa copied to clipboard

early stopping for nlp logics

Open seungwookim opened this issue 7 years ago • 0 comments

need to stop train when nlp networks (seq2seq, word2vec, doc2vec) reaches certain goal to prevent overfitting and save cpu powers

seungwookim avatar Apr 18 '17 06:04 seungwookim