Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/torch/nn.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2014-11-25Merge pull request #107 from ajtulloch/classnllcriterionSoumith Chintala
Support CUDA implementation of ClassNLLCriterion
2014-11-24[Torch] Move test.lua to the top levelAndrew Tulloch
Summary: This removes some CMakeLists.txt manipulation. Test Plan: ``` luarocks make rocks/nn-scm-1.rockspec && th -lnn -e "nn.test()" ... Completed 710 asserts in 81 tests with 0 errors ```
2014-11-24Merge pull request #109 from deltheil/masterSoumith Chintala
doc: link to the official Torch7 repo
2014-11-24doc: link to the official Torch7 repoCédric Deltheil
2014-11-22fix for euclidian patch from #108Soumith Chintala
2014-11-21Merge pull request #108 from ajtulloch/luacheck-configSoumith Chintala
[Torch] LuaCheck config file and fixes to make lint clean
2014-11-21Fix various unused variables in nnAndrew Tulloch
2014-11-21Fixed bug from unused scale variable in EuclideanAndrew Tulloch
2014-11-21Added LuacheckrcAndrew Tulloch
2014-11-21Support CUDA implementation of ClassNLLCriterionAndrew Tulloch
2014-11-18Merge pull request #106 from ajtulloch/sum-fixSoumith Chintala
[Torch] Fix `Sum:updateGradInput()` in the zero-stride case.
2014-11-18[Torch] Fix `Sum:updateGradInput()` in the zero-stride case.Andrew Tulloch
2014-11-18Merge branch 'master' of git://github.com/torch/nnRonan Collobert
2014-11-18fix 1D case for Mean/Sum/Max/MinRonan Collobert
2014-11-18global variable fixes (found via th -g)soumith
2014-11-18Merge pull request #102 from ajtulloch/jacobian-concurrencySoumith Chintala
[Torch] Make Jacobian.testIO safe for concurrent runs
2014-11-17generic/LogSoftMax speedupsAndrew Tulloch
2014-11-17Jacobian concurrencyAndrew Tulloch
2014-11-14bugfix for SpatialConvolutionMM and non-contiguous casesSoumith Chintala
2014-11-14Merge pull request #100 from nicholas-leonard/dropoutSoumith Chintala
Dropout can use torch.CudaTensor:bernoulli()
2014-11-13Dropout can use torch.CudaTensor:bernoulli()Nicholas Leonard
2014-11-12Merge pull request #99 from nicholas-leonard/lookupSoumith Chintala
LookupTable fixes and optimizations
2014-11-11LookupTable fixes and optimizationsNicholas Leonard
2014-11-11Merge pull request #97 from Aysegul/BatchModeFixSoumith Chintala
Batchmode is added to SpatialConvolutionMap
2014-11-10Merge pull request #96 from kaishengtai/fastlookuptableSoumith Chintala
Performance improvement to LookupTable
2014-11-10Performance improvement to LookupTableKai Sheng Tai
2014-11-10Batchmode is added to SpatialConvmapAysegul Dundar
2014-11-04Merge pull request #94 from nicholas-leonard/LookupTableSoumith Chintala
removed global variable in LookupTable
2014-11-04removed global variable in LookupTablenicholas-leonard
2014-11-04Merge pull request #93 from nicholas-leonard/AddSoumith Chintala
nn.Add works with batches
2014-11-04nn.Add works with batchesnicholas-leonard
2014-10-29Merge pull request #90 from fidlej/topic_gradInput_sizeSoumith Chintala
Updated CSubTable to have gradInput[2]:size() equal to input[2]:size().
2014-10-29Updated CSubTable to have gradInput[2]:size() equal to input[2]:size().Ivo Danihelka
2014-10-28fixing concat in the case when gradInput is not emmittedsoumith
2014-10-27TypoJonathan Hunt
2014-10-27adding scale to accGradParameters documentationSoumith Chintala
2014-10-27Relax equality tests from exact precision 0.GeorgOstrovski
Expecting exact precision 0 can lead to failing tests if underlying implementation changes, a high expected precision of say 1e-15 seem more appropriate (nntest.Power sometimes fails because of this)
2014-10-27Faster unit testsnicholas-leonard
2014-10-27adding addtional weights parameter to ClassNLLCriterion, which is 1D tensor ↵Yossi Biton
assigning different weight to each class
2014-10-27modernized MarginCriterionSergey Zagoruyko
2014-10-27Fixed broken CosineDistance examples.Nicholas Dronen
2014-10-27Corrected getParamaters for partial viewsJames Kirkpatrick
Module:getParameters was incorrectly overwriting parameters that were partial views on larger storages.
2014-10-27DepthConcatnicholas-leonard
2014-10-27SpatialConvolutionMM now support on-the-fly zero-padding.Clement Farabet
Interface similar to cunn.SpatialConvolutionMM. To get a layer where osize == isize, do this: local ksize = 5 local padding = (ksize-1)/2 local n = nn.SpatialConvolutionMM(ni,no, ksize,ksize, 1,1, padding) Note: dW/dH still not supported on the CPU version (strides).
2014-10-27added msg to recursive testerNicholas Leonard
2014-10-27Fixed PairwiseDistance exampleGunnar Aastrand Grimnes
2014-10-27Fix DotProduct example errorGrisson Wang
missing "{" "}". x=torch.Tensor(1,2,3) => x=torch.Tensor({1,2,3}) y=torch.Tensor(4,5,6) => y=torch.Tensor({4,5,6})
2014-09-23adding CONTRIBUTING guidelinesSoumith Chintala
2014-09-03Merge pull request #66 from timharley/masterSoumith Chintala
Give better error messages when trying to use the wrong kind of Tensor.
2014-09-03Give better error messages when trying to use the wrong kind of Tensor.Tim Harley
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-24 19:35:14 +0300