Age | Commit message (Collapse) | Author | |
---|---|---|---|
2014-07-10 | added accUpdate to nn.LookupTable | nicholas-leonard | |
2014-07-10 | Merge pull request #32 from nicholas-leonard/master | Soumith Chintala | |
rename ElementTable -> SelectTable | |||
2014-07-10 | Merge github.com:torch/nn into concattable_tableinput | Soumith Chintala | |
2014-07-10 | rename ElementTable -> SelectTable | nicholas-leonard | |
2014-07-10 | ReLU unit test | nicholas-leonard | |
2014-07-10 | added Dropout version 2 | nicholas-leonard | |
2014-07-09 | Merge branch 'master' of github.com:torch/nn into nnx | nicholas-leonard | |
2014-07-09 | Dropout unit tests | nicholas-leonard | |
2014-07-09 | ElementTable unit tests | nicholas-leonard | |
2014-07-08 | updated 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. | |||
2014-07-01 | typo | Soumith Chintala | |
2014-07-01 | Merge github.com:torch/nn into linear_fix | Soumith Chintala | |
2014-07-01 | Fixed the Linear stage when the output size is 1. | Jonathan Tompson | |
2014-06-30 | Add setNumInputDims() method to nn.View | Sergio Gomez | |
This allows to use minibatches when using -1 for one of the sizes. | |||
2014-06-27 | removed fprop test for SpatialUpSamplingNearest. | Jonathan Tompson | |
2014-06-26 | Added SpatialUpSamplingNearest module. | Jonathan Tompson | |
2014-06-26 | Merge pull request #20 from sergomezcol/view_module | Soumith Chintala | |
Add nn.View module | |||
2014-06-26 | Merge pull request #17 from sergomezcol/master | Soumith Chintala | |
Add minibatch support for nn.JoinTable and nn.SplitTable | |||
2014-06-26 | Add nn.View module | Sergio Gomez | |
This module creates a new view of the input tensor without copying it. | |||
2014-06-26 | Remove setNumInputDims method in JoinTable and SplitTable | Sergio Gomez | |
Now nInputDims is an optional parameter in the constructor of these modules. | |||
2014-06-25 | Add minibatch support for nn.JoinTable and nn.SplitTable | Sergio 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. | |||
2014-06-25 | Added very simple add and mul constant modules. | Jonathan Tompson | |
2014-06-18 | Update test.lua | GeorgOstrovski | |
2014-06-18 | changed precison threshold for LogSoftmax test | GeorgOstrovski | |
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. | |||
2014-05-13 | modified TemporalMaxPooling unit test to capture corner case | nicholas-leonard | |
2014-05-13 | fixed batch TemporalConvolution bug | nicholas-leonard | |
2014-05-12 | criterionJacobianTest -> criterionJacobianTest1D | Soumith Chintala | |
2014-05-12 | fixing BCECriterion, adding test, closing https://github.com/torch/nn/pull/10 | Soumith Chintala | |
2014-05-12 | Merge branch 'master' of github.com:torch/nn | Soumith Chintala | |
2014-05-12 | adding test for MSECriterion, fixed test for WeightedMSECriterion | Soumith Chintala | |
2014-05-11 | TemporalMaxPooling batch unit tests | nicholas-leonard | |
2014-05-11 | fixing temporalconvolutiobatch test | Soumith Chintala | |
2014-05-11 | missing , | Soumith Chintala | |
2014-05-10 | TemporalConvolution unit test 1D vs 2D | nicholas-leonard | |
2014-05-10 | TemporalConvolution unit test | nicholas-leonard | |
2014-04-10 | Added scaleUpdateByKey method. Refactored fairscale into separate file. | nicholas-leonard | |
Author: nicholas-leonard <nick@nikopia.org> | |||
2014-04-10 | unit tests complete | Nicholas Leonard | |
2014-04-10 | unit test for 1D LookupTable | Nicholas Leonard | |
2014-03-11 | return the tester object if another framework wants to use it. | koray kavukcuoglu | |
2014-02-01 | Added one more test for SparseLinear | Páidí Creed | |
2014-02-01 | Add extra tests for SparseLinear and fix bug where scale was not being ↵ | Páidí Creed | |
multiplied into bias updates | |||
2014-01-28 | Merge remote-tracking branch 'upstream/master' | Páidí Creed | |
2013-11-06 | Merge remote-tracking branch 'upstream/master' | Páidí Creed | |
Conflicts: extra/nn/test/test.lua | |||
2013-10-29 | Fix SparseLinear | Páidí Creed | |
Fixed an issue with SparseLinear and added a test along with a new class SparseJacobian (for testing sparse modules) | |||
2013-10-20 | fixed 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. | |||
2013-10-19 | Fixed 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. | |||
2013-10-15 | add 3D max pooling | koray kavukcuoglu | |
2013-09-27 | remove WeightedMSECriterion test since it fails with an unknown module | koray kavukcuoglu | |
2013-01-03 | New NN classes | koray 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 | |||
2012-10-12 | Made the private functions to be local. | Ivo Danihelka | |