Commit Graph

82 Commits

Author SHA1 Message Date
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
Ronny
26a492acf3 Update docstring for ConvTranspose functions
Transposed convolutions are often (but incorrectly) referred to as Deconvolutional operations. Made mention of this in the docstring to make it easier for people to search for this operation in the documentation.
2017-01-19 13:02:58 +01:00
Sam Gross
3a07228509 Add ConvTranspose1d module (#449) 2017-01-13 15:22:57 -05:00
Soumith Chintala
39ab5bcba8 fix MaxPool1d,2d,3d docs for rst 2017-01-04 03:11:48 -05:00
Soumith Chintala
42f131c09f fixing nn.Conv* documentation for rst and adding nn docs to sphinx 2017-01-04 02:11:27 -05:00
Sam Gross
64ca584199 Fix group support in convolution modules (#374) 2016-12-29 20:01:39 -05:00
Sam Gross
c367e0b64e Support dilated 1d and 3d convolutions (#372)
Fixes #367
2016-12-29 18:20:32 -05:00
Sergey Zagoruyko
239ae94389 fix in conv repr 2016-12-29 17:30:46 -05:00
Sergey Zagoruyko
62af45d99f Basic functional interface (#354) 2016-12-29 22:53:57 +01:00
Sam Gross
8a29338837 Use cuDNN for Conv3d and ConvTranspose3d (#359)
I've also updated test_nn.py to run marked tests twice: once with cuDNN
enabled and once with it disabled.
2016-12-28 16:14:47 -05:00
Sergey Zagoruyko
45d6212fd2 default args for conv functions 2016-12-25 01:55:00 -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
Adam Paszke
e51d0bef97 Add cuDNN bindings for 2D transposed convolution 2016-11-17 14:34:40 -08:00
Soumith Chintala
26d626a47c adding docs for loss functions, container, module and fix typos 2016-11-17 15:11:27 -05:00
soumith
071e68d99d fixing output size w / h order 2016-11-16 15:32:18 -08:00
Adam Paszke
78c1094d93 Don't override __call__ in modules 2016-11-16 15:32:18 -08:00
Soumith Chintala
513d902df1 adding __repr__ for nn 2016-11-07 16:17:40 -05:00
Adam Paszke
34bcd4c237 Rename FullConv to ConvTranspose and allow specifying output size 2016-10-10 20:51:15 -07:00
Adam Lerer
1213149a2f add bias option to linear; allow modules to return nested lists/tuples of tensors (#106)
* add bias option to linear; allow modules to return nested lists/tuples of tensors
2016-10-06 15:59:12 -04:00
Adam Paszke
3cbe66ba8c Change requires_grad default to False 2016-10-05 08:46:34 -07:00
soumith
d92b7da733 fix documentation to not use forward 2016-09-30 09:49:30 -07:00
Sam Gross
bab7f89cdc Fix no_bias constructor for conv2d (#65) 2016-09-28 19:30:43 -04:00
Adam Paszke
7f4ff0e615 Fix type conversions in nn 2016-09-27 15:45:49 -07:00
Adam Paszke
f9d25e8e72 Refactor nn (require specifying parameters explicitly) 2016-09-27 15:22:26 -07:00
Sam Gross
779a460030 Add cuDNN support for convolutions (#36) 2016-09-27 17:55:04 -04:00
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
Sam Gross
cd0929aa5e Use chainer-style constructor for Conv2d
* Conv2d, MaxPool2d, and AvgPool2d have one argument for each of ksize,
   stride, and pad. This argument can be either a single number or a
   tuple of (h, w)
2016-09-07 15:51:44 -07:00
Sam Gross
b738b09606 Clean up Module forward and __call__ (#14)
* _forward is renamed forward since users should override it

 * some __call__ overrides are changed to forward

 * function which return a single variable are changed to return that
   variable instead of a one-element tuple
2016-09-07 15:41:39 -04:00
Sam Gross
9553e46ed7 Make bias optional in Conv2d 2016-09-01 12:38:34 -07:00
Adam Paszke
ea93fb7ac0 Add more nn modules 2016-08-23 19:15:21 -07:00