Age | Commit message (Collapse) | Author | |
---|---|---|---|
2014-05-13 | fixed batch TemporalConvolution bug | nicholas-leonard | |
2014-05-11 | TemporalMaxPooling:updateGradInput | nicholas-leonard | |
2014-05-11 | fix TemporalMaxPooling:updateOutput segmentation fault | nicholas-leonard | |
2014-05-11 | TemporalMaxPooling:updateOutput | nicholas-leonard | |
2014-05-10 | TemporalConvolution:accGradParameters() | nicholas-leonard | |
2014-05-10 | fixed TemporalConvolution:inputGrad() bug | nicholas-leonard | |
2014-05-10 | TemporalConvolution:backward | nicholas-leonard | |
2014-05-09 | TemporalConvolution:forward() runs | nicholas-leonard | |
2014-05-09 | TemporalConvolution_updateOutput simple batch fix | nicholas-leonard | |
2014-05-09 | TemporalConvolution accepts batches | nicholas-leonard | |
2014-02-07 | fix SparseLinear debug printf | Ronan Collobert | |
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 | |
2013-11-27 | less strict about ansi libraries, less warnings | Leon Bottou | |
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) | |||
2013-10-16 | C89 | Ronan Collobert | |
2013-10-15 | add 3D max pooling | koray kavukcuoglu | |
2013-10-13 | move index declaragtion into pragma | koray kavukcuoglu | |
2013-10-13 | move k into thread private loop | koray kavukcuoglu | |
2013-10-08 | pkg/nn: C89 | Ronan Collobert | |
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 | |||
2012-09-28 | cleanup: useless variable | Ronan Collobert | |
2012-09-28 | code cleanup + removed dH/dW useless options | Ronan Collobert | |
2012-09-27 | SpatialMaxPooling: batch parallelized over... the batch | Ronan Collobert | |
2012-09-26 | surfing with the gflops | Ronan Collobert | |
2012-09-26 | add batch mode to SpatialMaxPooling and openmpize. | Koray Kavukcuoglu | |
2012-09-25 | mm-based convolutions now official | Ronan Collobert | |
2012-09-14 | corrected bug in backward of nn.Square | koray kavukcuoglu | |
2012-08-13 | nn package now complies with new luaT API | Ronan Collobert | |
2012-07-25 | added temporal max pooling | Ronan Collobert | |
2012-03-14 | Fixed bug in Sqrt/Square | Clement Farabet | |
2012-03-14 | Fixed SpatialMaxPooling bug. | Clement Farabet | |
2012-03-13 | Trying to merge openmp into main libs. | Clement Farabet | |
2012-03-01 | corrected a lot of warnings, mostly due to unused variables | Ronan Collobert | |
2012-02-04 | Merge branch 'master' into newpack | Ronan Collobert | |
2012-02-03 | Merge branch 'master' into newpack | Ronan Collobert | |
2012-01-30 | Merge branch 'master' into newpack | Ronan Collobert | |
Conflicts: extra/nn/test/test.lua | |||
2012-01-25 | initial revamp of torch7 tree | Ronan Collobert | |