gauravbaruah f91f105568 fixed variable perf bug and added debug arg for testing on each epoch (#2)
Because of random word embedding for out of vocabulary words, the performance of the final saved model was variable. This is now fixed.
2017-03-30 12:33:20 -04:00

Castor

Pytorch deep learning models.

  1. SM model: Similarity between question and candidate answers.
S
Description
PyTorch deep learning models for text processing
Readme Apache-2.0
1.2 MiB
0 Stars 1 Watchers 0 Forks
Languages
Python 93.7%
JavaScript 3.2%
Java 2.2%
HTML 0.5%
Shell 0.4%