Commit Graph

17 Commits

Author SHA1 Message Date
Adam Fisch
27bd3df71b Patching EmeddingBag to accept 2D input (#2429)
* Patching EmeddingBag to accept 2D input

* fix for CUDA inputs

* fix lint
2017-08-23 07:12:21 -04:00
Edward Z. Yang
f3f478960e Convert Embedding to new style. (#1916)
Signed-off-by: Edward Z. Yang <ezyang@fb.com>
2017-07-20 02:35:21 -04:00
Soumith Chintala
20ce45b0c3 fix EmbeddingSum offsets initialization 2017-07-13 02:57:25 -04:00
Soumith Chintala
f61ec2495e nn.EmbeddingBag to compute a bag of word embeddings (Embedding + Sum/Mean) 2017-06-15 12:32:47 -04:00
Soumith Chintala
2ef7331007 Update sparse.py 2017-04-27 02:25:00 +02:00
Luke Yeager
79f5bf84e5 [pep8] Potentially breaking docstring changes 2017-01-28 01:15:51 +01:00
Luke Yeager
e7c1e6a8e3 [pep8] Fix most lint automatically with autopep8
Here's the command I used to invoke autopep8 (in parallel!):

    git ls-files | grep '\.py$' | xargs -n1 -P`nproc` autopep8 -i

Several rules are ignored in setup.cfg. The goal is to let autopep8
handle everything which it can handle safely, and to disable any rules
which are tricky or controversial to address. We may want to come back
and re-enable some of these rules later, but I'm trying to make this
patch as safe as possible.

Also configures flake8 to match pep8's behavior.

Also configures TravisCI to check the whole project for lint.
2017-01-28 01:15:51 +01:00
Adam Lerer
3152be5fb3 Add repr to RNNs and Embedding (#428) 2017-01-13 15:53:52 -05:00
Zeming Lin
59d66e6963 Sparse Library (#333) 2017-01-05 00:43:41 +01:00
Soumith Chintala
7fa60b2e44 fixing docs of activations, pixelshuffle, sparse for rst 2017-01-04 18:40:51 -05:00
Sam Gross
ffcc38cf05 Deterministic ordering of parameters and buffers. (#317)
Uses the assignment syntax to get deterministic ordering of parameters.
The ordering of parameters using the constructor syntax is
non-deterministic because kwargs use dict() in Python 3.5 and earlier.
2016-12-16 14:45:56 -05:00
soumith
59c628803a fixing padding_idx option 2016-10-14 15:05:21 -07:00
Adam Paszke
3cbe66ba8c Change requires_grad default to False 2016-10-05 08:46:34 -07:00
Adam Paszke
f9d25e8e72 Refactor nn (require specifying parameters explicitly) 2016-09-27 15:22:26 -07:00
Adam Paszke
eec0420eb3 Initialize nn modules' parameters with a default tensor type 2016-09-23 18:06:26 -07:00
Soumith Chintala
5114d94ad9 docstrings for conv, dropout, linear, pooling and sparse functions 2016-09-19 00:31:22 -04:00
Adam Paszke
fb39971464 Add more modules to nn 2016-09-14 11:05:56 -07:00