saymrwulf/pytorch
1
0
Fork 0
mirror of https://github.com/saymrwulf/pytorch.git synced 2026-05-15 21:00:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
1139 commits 5021 branches 1206 tags 1 GiB
Commit graph

10 commits

Author SHA1 Message Date
Aaron Markham
58f7f2b441 doxygen python block added 
Summary: Closes https://github.com/caffe2/caffe2/pull/226

Differential Revision: D4793550

Pulled By: JoelMarcey

fbshipit-source-id: cc33e58186304fa8dcac2ee9115dcc271d785b1e
 2017-03-29 06:46:16 -07:00
Deepak Gopinath
422c65ca35 Removing unnecessary Copy after fixing gradients for external parameters 
Summary: Apart from copying gradient blobs for inputs with initial_cell_input, we needed to perform a similar operation for external parameters used by the step net

Reviewed By: salexspb

Differential Revision: D4752259

fbshipit-source-id: 13ee48cf583ed86221a4cc1cc9f57f5c3a7d2450
 2017-03-23 15:04:22 -07:00
Yury Zemlyanskiy
ea66516d5e Output attention weights from apply_xxx_attention methods 
Summary: OSS diff. We need it later for beam decoding.

Differential Revision: D4747785

fbshipit-source-id: ce2d53ee2434216ace3c4ddbd40a9b68e9db7ec5
 2017-03-21 19:01:58 -07:00
Yury Zemlyanskiy
93ff338ca7 Beam decoder for NMT in Caffe2 
Summary: yolo5

Differential Revision: D4685076

fbshipit-source-id: b5534e441bb453f90e5210294f2dfff6b5c3b5b1
 2017-03-20 22:03:59 -07:00
James Reed
33f41c06c0 Remove more instances of batch_size 
Summary: D4734505 part 2. Remove more instances of the batch_size parameter

Reviewed By: urikz

Differential Revision: D4736906

fbshipit-source-id: fc9d374e9308017d61c427890364c5ab9cec2edf
 2017-03-19 22:31:30 -07:00
James Reed
17da5856ed Remove batch_size parameter from attention and LSTMWithAttention interfaces 
Summary: Reshape based on tensor shapes in the graph rather than based on a passed-in batch_size parameter

Reviewed By: urikz

Differential Revision: D4734505

fbshipit-source-id: d9c23d85be84f61124106e752ef2b4f6945e2a07
 2017-03-19 18:16:28 -07:00
Yury Zemlyanskiy
d1424c3265 Revert D4702086: Remove batch_size parameter from attention and LSTMWithAttention interfaces 
Summary: This reverts commit c4c1d8425cd36c1e86695918eaba2667c27e9601

Differential Revision: D4702086

fbshipit-source-id: 4620610b182bb84b9297b5de32782761ae89d20b
 2017-03-17 17:36:47 -07:00
James Reed
10d95bd0f0 Remove batch_size parameter from attention and LSTMWithAttention interfaces 
Summary: Reshape based on tensor shapes in the graph rather than based on a passed-in batch_size parameter

Reviewed By: urikz

Differential Revision: D4702086

fbshipit-source-id: c4c1d8425cd36c1e86695918eaba2667c27e9601
 2017-03-16 11:47:52 -07:00
James Reed
8de1db9eb6 Implement recurrent attention in C2 
Summary: Super rough implementation of recurrent attention. Planning to factor out the common code between the two functions as well as train and eval. I want to get this out and get eyes on it sooner rather than later

Differential Revision: D4647837

fbshipit-source-id: 54bc4e8ed0df6f04c86c425926decbe89f73b068
 2017-03-08 11:21:28 -08:00
Yury Zemlyanskiy
4a53ab3cb6 LSTMWithAttention implementation in Caffe2 
Summary:
Implementation of ##LSTMWithAttention##

Still TBD:
1. There are problems with back propagation, because gradient is not implemented for ops with broadcasting
2. I need to make initial_recurrent_state to be of shape [dim] rather than [1, batch_size, dim], so one doesn't need to provide batch_size to LSTMWithAttention

Differential Revision: D4298735

fbshipit-source-id: 8903fcff4d6a66647ee6d45a6ef28803fc3091e5
 2017-02-23 04:08:34 -08:00