Juan Miguel Pino 4d8a8c2e1e Implement dot attention ... Summary: Implement dot attention as described in https://arxiv.org/abs/1508.04025 This saves the computation of weighted encoder outputs in `rnn_cell.py` When the encoder and decoder dimensions are different, we apply an FC, which corresponds to the general case below Figure 2. Refactored unit tests. Reviewed By: jhcross Differential Revision: D5486976 fbshipit-source-id: f9e9aea675b3b072fbe631bc004199b90a9d95cb		2017-08-06 11:50:16 -07:00
..
seq2seq	Implement dot attention	2017-08-06 11:50:16 -07:00
__sym_init__.py	exec_net --> predict_net	2017-03-23 16:31:49 -07:00
download.py	fix download progress bar's percentage exceed 100%	2017-04-20 10:41:06 -07:00
resnet.py	Fix a few typos and grammars in comment	2017-06-14 18:22:39 -07:00
resnet_test.py	fast simple-net memonger for C++	2017-07-06 15:17:07 -07:00