OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-07 12:21:27 +01:00
Code Issues Actions 37 Packages Projects Releases Wiki Activity
94,103 Commits 8,304 Branches 150 Tags 1.5 GiB
c855f8632e
Commit Graph

189 Commits

Author SHA1 Message Date
Edward Z. Yang
96a281dfab Add one more missing self.dilation parameter. (#1392) 
Signed-off-by: Edward Z. Yang <ezyang@fb.com>
 2017-04-28 19:16:32 +02:00
Edward Z. Yang
7e8ef0e22a Actually pass dilation to the underlying operators. (#1386) 
No tests for now; we'll need some sort of shape DSL to concisely
represent them.

Signed-off-by: Edward Z. Yang <ezyang@fb.com>
 2017-04-27 23:38:01 +02:00
Edward Z. Yang
34546f022a Expose dilated convolutions. 
Fixes #1225.

Signed-off-by: Edward Z. Yang <ezyang@fb.com>
 2017-04-18 17:13:02 -04:00
Gu Wang
170d790b66 fix doc of conv3d in conv.py (#989) 
the second dimension should be height.
 2017-03-13 11:30:13 -04:00
Alfredo Canziani
385913be1c Fix class torch.nn.ConvTransposeNd documentation (#739) 
There is no `dilation`
`output_padding` doc was missing
 2017-02-15 10:37:20 +05:30
Luke Yeager
79f5bf84e5 [pep8] Potentially breaking docstring changes 2017-01-28 01:15:51 +01:00
Luke Yeager
3ed720079e [pep8] Fix most remaining lint manually 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
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