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
path: root/test
AgeCommit message (Collapse)Author
2014-07-10added accUpdate to nn.LookupTablenicholas-leonard
2014-07-10Merge pull request #32 from nicholas-leonard/masterSoumith Chintala
rename ElementTable -> SelectTable
2014-07-10Merge github.com:torch/nn into concattable_tableinputSoumith Chintala
2014-07-10rename ElementTable -> SelectTablenicholas-leonard
2014-07-10ReLU unit testnicholas-leonard
2014-07-10added Dropout version 2nicholas-leonard
2014-07-09Merge branch 'master' of github.com:torch/nn into nnxnicholas-leonard
2014-07-09Dropout unit testsnicholas-leonard
2014-07-09ElementTable unit testsnicholas-leonard
2014-07-08updated ConcatTable so that it works with table inputs as well as tensors.Jonathan Tompson
removed a temporary line. added a test for getParameters to ConcatTable.
2014-07-01typoSoumith Chintala
2014-07-01Merge github.com:torch/nn into linear_fixSoumith Chintala
2014-07-01Fixed the Linear stage when the output size is 1.Jonathan Tompson
2014-06-30Add setNumInputDims() method to nn.ViewSergio Gomez
This allows to use minibatches when using -1 for one of the sizes.
2014-06-27removed fprop test for SpatialUpSamplingNearest.Jonathan Tompson
2014-06-26Added SpatialUpSamplingNearest module.Jonathan Tompson
2014-06-26Merge pull request #20 from sergomezcol/view_moduleSoumith Chintala
Add nn.View module
2014-06-26Merge pull request #17 from sergomezcol/masterSoumith Chintala
Add minibatch support for nn.JoinTable and nn.SplitTable
2014-06-26Add nn.View moduleSergio Gomez
This module creates a new view of the input tensor without copying it.
2014-06-26Remove setNumInputDims method in JoinTable and SplitTableSergio Gomez
Now nInputDims is an optional parameter in the constructor of these modules.
2014-06-25Add minibatch support for nn.JoinTable and nn.SplitTableSergio Gomez
The method setNumInputDims allows forwarding both minibatch and non-minibatch tensors through the same module. If this method is not used, the behaviour of these modules is the same as before.
2014-06-25Added very simple add and mul constant modules.Jonathan Tompson
2014-06-18Update test.luaGeorgOstrovski
2014-06-18changed precison threshold for LogSoftmax testGeorgOstrovski
The previous threshold was insufficient and the test occasionally failed. I ran it a large number of times (~1e5) and the actual error reached ~ 2x1e-4, so I propose 3*1e-10 as the new safer threshold.
2014-05-13modified TemporalMaxPooling unit test to capture corner casenicholas-leonard
2014-05-13fixed batch TemporalConvolution bugnicholas-leonard
2014-05-12criterionJacobianTest -> criterionJacobianTest1DSoumith Chintala
2014-05-12fixing BCECriterion, adding test, closing https://github.com/torch/nn/pull/10Soumith Chintala
2014-05-12Merge branch 'master' of github.com:torch/nnSoumith Chintala
2014-05-12adding test for MSECriterion, fixed test for WeightedMSECriterionSoumith Chintala
2014-05-11TemporalMaxPooling batch unit testsnicholas-leonard
2014-05-11fixing temporalconvolutiobatch testSoumith Chintala
2014-05-11missing ,Soumith Chintala
2014-05-10TemporalConvolution unit test 1D vs 2Dnicholas-leonard
2014-05-10TemporalConvolution unit testnicholas-leonard
2014-04-10Added scaleUpdateByKey method. Refactored fairscale into separate file.nicholas-leonard
Author: nicholas-leonard <nick@nikopia.org>
2014-04-10unit tests completeNicholas Leonard
2014-04-10unit test for 1D LookupTableNicholas Leonard
2014-03-11return the tester object if another framework wants to use it.koray kavukcuoglu
2014-02-01Added one more test for SparseLinearPáidí Creed
2014-02-01Add extra tests for SparseLinear and fix bug where scale was not being ↵Páidí Creed
multiplied into bias updates
2014-01-28Merge remote-tracking branch 'upstream/master'Páidí Creed
2013-11-06Merge remote-tracking branch 'upstream/master'Páidí Creed
Conflicts: extra/nn/test/test.lua
2013-10-29Fix SparseLinearPáidí Creed
Fixed an issue with SparseLinear and added a test along with a new class SparseJacobian (for testing sparse modules)
2013-10-20fixed a bug in Pairwise distance when the output Lp norm is zero (which ↵Jonathan Tompson
results in a divide by zero issue). Rewrote PairwiseDistance following Clement's suggestion to only have one codepath. Fixed a small bug in extra/test/test.lua where the input to the non-batch fprop test was zero.
2013-10-19Fixed the bprop in PairwiseDistance for pnorms other than one. The ↵Jonathan Tompson
gradInput has always been wrong it seems; the sign of the gradient is correct but the magnitude was wrong. I also added a test in extra/nn/test/test.lua for nn.PairwiseDifference, which tests both the batch and non-batch code paths for a few different p-norms.
2013-10-15add 3D max poolingkoray kavukcuoglu
2013-09-27remove WeightedMSECriterion test since it fails with an unknown modulekoray kavukcuoglu
2013-01-03New NN classeskoray kavukcuoglu
extra/nn/L1Cost.lua : L1 penalty extra/nn/SpatialFullConvolution.lua : full convolution extra/nn/SpatialFullConvolutionMap.lua : full convolution with connection table extra/nn/TanhShrink.lua : shrinkage with x-tanh(x) extra/nn/WeightedMSECriterion.lua : mean squared error with weighting mask on the target Add new nn classes that are used commonly for unsupervised training of convolutional auto encoders
2012-10-12Made the private functions to be local.Ivo Danihelka
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-13 03:50:17 +0300