5870d13 | Soumith Chintala | 17 October 2016, 04:30:25 UTC | fixes to upsampling bilinear API | 17 October 2016, 04:30:25 UTC |
9cabae0 | Soumith Chintala | 13 October 2016, 22:09:43 UTC | Merge pull request #351 from torch/revert-350-master Revert "change to work on windows && replace long with ptrdiff_t" | 13 October 2016, 22:09:43 UTC |
14c591d | Soumith Chintala | 13 October 2016, 22:09:34 UTC | Revert "change to work on windows && replace long with ptrdiff_t" | 13 October 2016, 22:09:34 UTC |
60a753a | Soumith Chintala | 13 October 2016, 16:25:59 UTC | Merge pull request #350 from BTNC/master change to work on windows && replace long with ptrdiff_t | 13 October 2016, 16:25:59 UTC |
4247d64 | Rui Guo | 13 October 2016, 15:44:28 UTC | change to work on windows && replace long with ptrdiff_t | 13 October 2016, 15:44:28 UTC |
e388ee3 | Soumith Chintala | 07 October 2016, 14:36:40 UTC | Merge pull request #338 from nitsky/spatial_logsoftmax SpatialLogSoftMax | 07 October 2016, 14:36:40 UTC |
612dda4 | Soumith Chintala | 30 September 2016, 16:12:32 UTC | Merge pull request #343 from colesbury/master Fixes for https://github.com/torch/cutorch/pull/519 | 30 September 2016, 16:12:32 UTC |
52f7419 | Sam Gross | 29 September 2016, 23:19:41 UTC | Fixes for https://github.com/torch/cutorch/pull/519 | 29 September 2016, 23:19:41 UTC |
9a3ffab | David Yamnitsky | 27 September 2016, 15:16:31 UTC | Fix SpatialLogSoftMax memory leak and code cleanup | 27 September 2016, 15:16:31 UTC |
5aa68bb | Soumith Chintala | 27 September 2016, 00:50:42 UTC | Merge pull request #339 from torch/classnllfix making ClassNLLCriterion targets consistent between cpu and cuda | 27 September 2016, 00:50:42 UTC |
9b3be1f | soumith | 27 September 2016, 00:48:17 UTC | making ClassNLLCriterion targets consistent between cpu and cuda | 27 September 2016, 00:48:17 UTC |
8e6bfc5 | David Yamnitsky | 26 September 2016, 16:39:56 UTC | Update SpatialLogSoftMax kernel to use cuda dimensions | 26 September 2016, 16:39:56 UTC |
d85eeca | fsuzanomassa | 14 January 2016, 15:08:31 UTC | Update LogSoftMax to work in spatial domain | 21 September 2016, 15:11:59 UTC |
10e9b68 | Soumith Chintala | 14 September 2016, 14:53:29 UTC | Merge pull request #334 from apaszke/header_fix Mark BCECriterion weights as optional in THCUNN.h | 14 September 2016, 14:53:29 UTC |
a8a1c77 | Adam Paszke | 14 September 2016, 14:36:59 UTC | Mark BCECriterion weights as optional in THCUNN.h | 14 September 2016, 14:36:59 UTC |
ccc2309 | soumith | 13 September 2016, 04:09:25 UTC | moving arch detetction into THCUNN | 13 September 2016, 04:09:25 UTC |
4a04229 | David Yamnitsky | 08 September 2016, 20:33:53 UTC | BCECriterion THCUNN + Weights (#331) BCE Criterion CUDA implementation | 08 September 2016, 20:33:53 UTC |
ecc4141 | Soumith Chintala | 06 September 2016, 17:52:21 UTC | Merge pull request #332 from vivekn/dpt_fix Fix issue with flatten parameters in DataParallelTable | 06 September 2016, 17:52:21 UTC |
e1d9cbc | Vivek Narayanan | 06 September 2016, 17:42:33 UTC | Fix issue with flatten parameters in DataParallelTable | 06 September 2016, 17:42:33 UTC |
cdac0c3 | Soumith Chintala | 01 September 2016, 02:36:26 UTC | Merge pull request #329 from gchanan/hardtanh inplace is reversed in HardTanh:backward. | 01 September 2016, 02:36:26 UTC |
dbbb218 | Gregory Chanan | 01 September 2016, 02:17:23 UTC | inplace is reversed in HardTanh:backward. Fixes torch7 issue #734, "Inconsistent behavior of nn.Clamp in CPU and GPU modes". Adds a simple test that gradOutput equals gradInput after backward when inplace is set. It is possible to construct a test with inplace HardTanh where forward+backward yields different results for nn vs cunn, but this appears to be due to the inclusive vs exclusive bounds used for inplace vs non-inplace, respectively, so a more direct test is preferred. | 01 September 2016, 02:31:41 UTC |
d652966 | Soumith Chintala | 27 August 2016, 18:02:44 UTC | Update README.md | 27 August 2016, 18:02:44 UTC |
b6e4a61 | Soumith Chintala | 27 August 2016, 14:42:05 UTC | Merge pull request #327 from kmul00/voldilmaxpool VolumetricDilatedMaxPooling | 27 August 2016, 14:42:05 UTC |
ec16b36 | kmul00 | 28 August 2016, 13:31:12 UTC | VolumetricDilatedMaxPooling modified: lib/THCUNN/THCUNN.h copied: lib/THCUNN/VolumetricMaxPooling.cu -> lib/THCUNN/VolumetricDilatedMaxPooling.cu modified: lib/THCUNN/VolumetricMaxPooling.cu modified: test.lua | 28 August 2016, 13:31:12 UTC |
a3ccbeb | Soumith Chintala | 26 August 2016, 23:17:15 UTC | Merge pull request #326 from kmul00/consistentapimaxpool Consistent Max Pool API | 26 August 2016, 23:17:15 UTC |
f8c82e5 | kmul00 | 26 August 2016, 20:09:14 UTC | Consistent Max Pool API renamed: lib/THCUNN/SpatialMaxPooling.cu -> lib/THCUNN/SpatialDilatedMaxPooling.cu modified: lib/THCUNN/SpatialMaxPooling.cu modified: lib/THCUNN/THCUNN.h | 26 August 2016, 20:09:14 UTC |
3c4a48a | Soumith Chintala | 24 August 2016, 20:27:10 UTC | fix Lua 5.2 compat | 24 August 2016, 20:27:10 UTC |
ef2c953 | soumith | 22 August 2016, 18:41:46 UTC | fix critical bug in SpatialConvolution | 22 August 2016, 18:41:46 UTC |
50c63ac | Soumith Chintala | 19 August 2016, 21:11:28 UTC | Merge pull request #323 from apaszke/threshold Make Threshold THCUNN functions more consistent | 19 August 2016, 21:11:28 UTC |
2298e03 | soumith | 18 August 2016, 20:06:57 UTC | updating cmake | 18 August 2016, 20:06:57 UTC |
d3f22ef | Adam Paszke | 18 August 2016, 17:24:04 UTC | Make Threshold THCUNN functions more consistent | 18 August 2016, 18:14:25 UTC |
d0e27d2 | Soumith Chintala | 18 August 2016, 14:25:20 UTC | Merge pull request #322 from apaszke/spatial_conv Accept both 2D and 4D weights in SpatialConvolutionMM | 18 August 2016, 14:25:20 UTC |
f075592 | Adam Paszke | 18 August 2016, 13:58:43 UTC | Accept both 2D and 4D weights in SpatialConvolutionMM | 18 August 2016, 13:58:43 UTC |
25498b7 | kmul00 | 11 August 2016, 07:19:25 UTC | CUDA version of Spatioal Dilated Max Pooling modified: lib/THCUNN/SpatialMaxPooling.cu modified: lib/THCUNN/THCUNN.h modified: test.lua | 12 August 2016, 15:00:02 UTC |
3040562 | Soumith Chintala | 12 August 2016, 03:47:49 UTC | Merge pull request #319 from torch/typesfix fixes for multiple cuda types | 12 August 2016, 03:47:50 UTC |
2618f79 | soumith | 12 August 2016, 01:06:05 UTC | fixes for multiple cuda types | 12 August 2016, 01:57:28 UTC |
65568cf | Soumith Chintala | 11 August 2016, 19:40:15 UTC | Merge pull request #318 from apaszke/master Improvements/fixes in THCUNN | 11 August 2016, 19:40:15 UTC |
fdf6fe4 | Adam Paszke | 11 August 2016, 19:37:11 UTC | Fix DistKLDivCriterion gradInput formula | 11 August 2016, 19:37:11 UTC |
8ae08a2 | Adam Paszke | 11 August 2016, 19:29:57 UTC | Use TH_INDEX_BASE in THCUNN | 11 August 2016, 19:31:31 UTC |
1b76671 | Adam Paszke | 11 August 2016, 19:29:41 UTC | Mark optional arguments in THCUNN.h | 11 August 2016, 19:31:14 UTC |
ccba310 | Soumith Chintala | 10 August 2016, 16:51:55 UTC | Merge pull request #316 from apaszke/master Fix THCUNN.h formatting | 10 August 2016, 16:51:55 UTC |
75e4228 | Adam Paszke | 10 August 2016, 16:33:40 UTC | Fix THCUNN.h formatting | 10 August 2016, 16:33:40 UTC |
6409c15 | Soumith Chintala | 05 August 2016, 21:07:07 UTC | Merge pull request #314 from colesbury/bn Fix "invalid configuration" when using very large batch sizes in evaluate mode | 05 August 2016, 21:07:07 UTC |
49fdc1c | Sam Gross | 05 August 2016, 20:44:26 UTC | Fix "invalid configuration" when using very large batch sizes in evaluate mode. Example: ``` bn = nn.BatchNormalization(100):cuda() bn:evaluate() bn:forward(torch.CudaTensor(147000, 100):zero()) cutorch.synchronize() ``` Fixes https://github.com/torch/nn/issues/907 | 05 August 2016, 20:44:26 UTC |
7f27d6a | Soumith Chintala | 04 August 2016, 04:41:05 UTC | Merge pull request #313 from torch/voldilcol Volumetric Dilated Convolution | 04 August 2016, 04:41:05 UTC |
d7ee9c6 | soumith | 04 August 2016, 04:04:52 UTC | Volumetric Dilated Convolution | 04 August 2016, 04:29:30 UTC |
b592695 | Soumith Chintala | 02 August 2016, 15:50:26 UTC | Merge pull request #312 from torch/softfix fix SpatialSoftMax bug and add unit tests | 02 August 2016, 15:50:26 UTC |
0bd7346 | soumith | 02 August 2016, 15:48:48 UTC | fix SpatialSoftMax bug and add unit tests | 02 August 2016, 15:48:48 UTC |
2b31650 | Soumith Chintala | 29 July 2016, 23:39:50 UTC | adding new arch selector | 29 July 2016, 23:39:50 UTC |
8c4e9d5 | Soumith Chintala | 29 July 2016, 05:47:01 UTC | Merge pull request #310 from torch/cutorch-Sgemm-compat gemm -> Sgemm | 29 July 2016, 05:47:01 UTC |
84d3746 | Sergey Zagoruyko | 29 June 2016, 16:06:10 UTC | gemm -> Sgemm | 29 July 2016, 05:45:08 UTC |
208e1fa | Soumith Chintala | 29 July 2016, 05:08:40 UTC | add versioning script | 29 July 2016, 05:08:40 UTC |
e856c86 | Soumith Chintala | 29 July 2016, 05:04:49 UTC | Cutting version 1.0-0 | 29 July 2016, 05:04:49 UTC |
387ff4f | Soumith Chintala | 27 July 2016, 18:25:39 UTC | Merge pull request #309 from paulineluc14/master Adding SpatialUpSamplingBilinear | 27 July 2016, 18:25:39 UTC |
a6bb463 | Pauline Luc | 27 July 2016, 09:12:05 UTC | Adding SpatialUpSamplingBilinear | 27 July 2016, 09:12:05 UTC |
9634a07 | Soumith Chintala | 25 July 2016, 14:00:56 UTC | Merge pull request #308 from mys007/classnllbounds NLL Criteria: weight bound checking | 25 July 2016, 14:00:56 UTC |
3f14ce2 | Martin Simonovsky | 25 July 2016, 10:03:04 UTC | added bound checks for weights | 25 July 2016, 10:03:04 UTC |
2cd59e1 | Soumith Chintala | 07 July 2016, 23:19:19 UTC | Merge pull request #305 from colesbury/batchnorm Fix BatchNormalization warpSum for pre-Kepler cards | 07 July 2016, 23:19:19 UTC |
136b547 | Sam Gross | 07 July 2016, 23:12:58 UTC | Fix BatchNormalization warpSum for pre-Kepler cards Fixes #298 | 07 July 2016, 23:13:12 UTC |
86d9f56 | Soumith Chintala | 04 July 2016, 22:26:51 UTC | Merge pull request #303 from torch/powfix fix for std::pow ambiguousness | 04 July 2016, 22:26:51 UTC |
0732014 | soumith | 04 July 2016, 22:27:05 UTC | fix for std::pow ambiguousness | 04 July 2016, 22:27:05 UTC |
d02176d | Soumith Chintala | 03 July 2016, 12:39:23 UTC | Merge pull request #282 from nicholas-leonard/GPU nn.GPU | 03 July 2016, 12:39:23 UTC |
d642e59 | nicholas-leonard | 02 July 2016, 20:30:58 UTC | nn.GPU unit test | 02 July 2016, 20:31:06 UTC |
0e7f438 | Soumith Chintala | 23 June 2016, 18:57:27 UTC | Merge pull request #301 from PraveerSINGH/SpatialFullConvolution-noBias Add noBias for nn.SpatialFullConvolution | 23 June 2016, 18:57:27 UTC |
b80facc | PraveerSINGH | 23 June 2016, 13:22:39 UTC | nobias in spatial full conv | 23 June 2016, 13:22:39 UTC |
67c87ef | Soumith Chintala | 18 June 2016, 15:44:16 UTC | Merge pull request #300 from jonathantompson/volpad Added VolumetricReplicationPadding. | 18 June 2016, 15:44:16 UTC |
e5181dc | Soumith Chintala | 18 June 2016, 15:42:51 UTC | Merge pull request #299 from szagoruyko/inplace-hardtanh inplace hardtanh, remove relu6 | 18 June 2016, 15:42:51 UTC |
ca50de6 | Jonathan Tompson | 17 June 2016, 21:46:42 UTC | Added VolumetricReplicationPadding. | 17 June 2016, 21:46:42 UTC |
2ece1b2 | Sergey Zagoruyko | 16 June 2016, 15:08:32 UTC | inplace hardtanh, remove relu6 | 16 June 2016, 15:08:32 UTC |
55dd536 | Soumith Chintala | 14 June 2016, 20:59:37 UTC | Merge pull request #297 from jonathantompson/relu6 Added ReLU6 implementation and test. | 14 June 2016, 20:59:37 UTC |
caa0b94 | Jonathan Tompson | 14 June 2016, 18:42:16 UTC | Added ReLU6 implementation and test. | 14 June 2016, 18:50:48 UTC |
bf710ed | Soumith Chintala | 11 June 2016, 15:10:22 UTC | Merge pull request #294 from kmul00/volmaxunpool Added CUDA version of VolumetricMaxUnpooling | 11 June 2016, 15:10:22 UTC |
5312313 | Soumith Chintala | 11 June 2016, 14:59:47 UTC | Merge pull request #296 from torch/fixes fixes for cutorch API changes | 11 June 2016, 14:59:47 UTC |
b01894b | soumith | 11 June 2016, 14:59:09 UTC | fixes for cutorch API changes | 11 June 2016, 14:59:09 UTC |
5413524 | kmul00 | 10 June 2016, 11:56:13 UTC | Added CUDA version of VolumetricMaxUnpooling modified: THCUNN.h new file: VolumetricMaxUnpooling.cu modified: ../../test.lua Freed input storage modified: VolumetricMaxUnpooling.cu | 11 June 2016, 10:13:56 UTC |
bc1080e | soumith | 06 June 2016, 22:32:53 UTC | adding some comments | 06 June 2016, 22:32:53 UTC |
40049f6 | Soumith Chintala | 05 June 2016, 23:37:03 UTC | Merge pull request #291 from torch/volpoolfixx fixing Volumetric Average and Max Pooling for large inputs | 05 June 2016, 23:37:03 UTC |
d95c58e | soumith | 05 June 2016, 23:32:22 UTC | fixing Volumetric Average and Max Pooling for large inputs | 05 June 2016, 23:32:22 UTC |
e4e0a8c | Soumith Chintala | 05 June 2016, 06:15:34 UTC | Merge pull request #290 from torch/errcheck making error checking consistent, always and simple | 05 June 2016, 06:15:34 UTC |
b1a39d1 | soumith | 05 June 2016, 06:14:16 UTC | making error checking consistent, always and simple | 05 June 2016, 06:14:16 UTC |
4a14d88 | Soumith Chintala | 04 June 2016, 04:46:41 UTC | Merge pull request #288 from torch/gccfix fixes for gcc 5.xx | 04 June 2016, 04:46:41 UTC |
c67cfef | Soumith Chintala | 04 June 2016, 04:45:31 UTC | fixes for gcc 5.xx | 04 June 2016, 04:45:31 UTC |
6d31b76 | Soumith Chintala | 02 June 2016, 04:31:17 UTC | Merge pull request #287 from borisfom/master Improving arch selection function handling | 02 June 2016, 04:31:17 UTC |
913539d | Boris Fomitchev | 01 June 2016, 22:05:37 UTC | Improving arch selection function handling | 01 June 2016, 22:46:54 UTC |
597e858 | Soumith Chintala | 01 June 2016, 02:52:16 UTC | Merge pull request #285 from colesbury/dpt Fix test_DataParallelTable.lua | 01 June 2016, 02:52:16 UTC |
7296c27 | Sam Gross | 31 May 2016, 19:30:33 UTC | Fix test_DataParallelTable.lua | 31 May 2016, 19:30:33 UTC |
64d36c2 | Soumith Chintala | 28 May 2016, 02:40:50 UTC | Merge pull request #283 from torch/revert-281-master Revert "Poring to new CMake" | 28 May 2016, 02:40:50 UTC |
c605f3c | Soumith Chintala | 28 May 2016, 02:40:40 UTC | Revert "Poring to new CMake" | 28 May 2016, 02:40:40 UTC |
1342a08 | Soumith Chintala | 27 May 2016, 17:32:19 UTC | Merge pull request #281 from borisfom/master Poring to new CMake | 27 May 2016, 17:32:19 UTC |
c8730c6 | Boris Fomitchev | 26 February 2016, 06:26:58 UTC | Porting to new CMake | 26 May 2016, 22:43:00 UTC |
bd6659a | Boris Fomitchev | 29 January 2016, 01:18:43 UTC | Added CUDA 5.2 | 26 May 2016, 22:07:14 UTC |
00209fc | Soumith Chintala | 26 May 2016, 05:07:37 UTC | Merge pull request #279 from andreaskoepf/softmax_3d Use 3d thread blocks in SoftMax for inputs with w*h > 2^16-1 | 26 May 2016, 05:07:37 UTC |
6b02ea8 | Andreas Köpf | 20 May 2016, 21:57:45 UTC | Use 3d thread blocks in SoftMax for inputs with w*h > 2^16-1 | 20 May 2016, 21:57:45 UTC |
9b74238 | Soumith Chintala | 20 May 2016, 13:22:20 UTC | Merge pull request #277 from davidsaxton/fix_test Fix SpatialSubSampling (was doing non-atomic writes in backprop). | 20 May 2016, 13:22:20 UTC |
96a0bdb | David Saxton | 20 May 2016, 09:37:11 UTC | Fix SpatialSubSampling (was doing non-atomic writes in backprop). Also some changes to test to make it less flaky: - Decrease some output counts to reduce out-of-memory issues. - Decrease some tolerances. - Increase precision of random seed so that multiple test launches at the same time start with different seeds. | 20 May 2016, 09:37:11 UTC |
772e05c | Soumith Chintala | 18 May 2016, 14:53:01 UTC | Merge pull request #276 from hughperkins/readme-fixette readme fixette | 18 May 2016, 14:53:01 UTC |
ae9bb94 | Hugh Perkins | 18 May 2016, 09:48:05 UTC | readme fixette | 18 May 2016, 09:48:05 UTC |
aeb2e3f | Soumith Chintala | 18 May 2016, 05:13:55 UTC | Merge pull request #274 from verdimrc/verdimrc-patch-1 Limit registers when LRNFillScale runs on TK1. | 18 May 2016, 05:13:55 UTC |
6a59763 | Verdi March | 18 May 2016, 03:52:37 UTC | Limit registers when LRNFillScale runs on TK1. Fix for torch@cunn#271, to make openface works on Jetson TK1. | 18 May 2016, 03:52:37 UTC |
e7cc01c | Soumith Chintala | 17 May 2016, 23:20:03 UTC | Merge pull request #273 from hughperkins/readme-fixettes fixettes for README.md | 17 May 2016, 23:20:03 UTC |