Age | Commit message (Collapse) | Author | |
---|---|---|---|
2017-04-05 | Update to ignore zero targets | Jin-Hwa Kim | |
If the target is zero, loss and gradient of input are set to zero. It is useful for variable-length natural language generation models. | |||
2017-03-31 | Merge pull request #456 from twitter-forks/addmm-fixes | Soumith Chintala | |
Using temporary variables when performing transpose + addmm | |||
2017-03-30 | Using temporary variables when performing transpose + addmm | Pavan Yalamanchili | |
2017-03-25 | Improving the performance of IndexLinear:updateOutput | Pavan Yalamanchili | |
- Removes separate kernel for updateOutputTrain | |||
2017-03-24 | Merge pull request #454 from ngimel/patch-1 | Soumith Chintala | |
Fix inconsistent in-place and out-of-place for HardTanh | |||
2017-03-24 | Fix inconsistent in-place and out-of-place for HardTanh | ngimel | |
in-place and out-of-place updateGradOutput results are different where input=min_val or input=max_val | |||
2017-03-24 | Adding support for flattened inputs for IndexLinear | Pavan Yalamanchili | |
- Adding relevant tests | |||
2017-03-24 | IndexLinear support for cunn | Pavan Yalamanchili | |
2017-03-22 | Merge pull request #453 from apaszke/lookup_renorm | Soumith Chintala | |
Cast accumulator in LookupTable renorm to accreal | |||
2017-03-22 | Added support for multidimensional tensors in PReLU; Channel number now in ↵ | Hardik | |
second dimension | |||
2017-03-22 | Cast accumulator in LookupTable renorm to accreal | Adam Paszke | |
2017-03-15 | Merge pull request #449 from gchanan/precision_testing | Soumith Chintala | |
Improve precision testing | |||
2017-03-15 | Merge pull request #451 from wickedfoo/faster-lookup-table | Soumith Chintala | |
Improve cunn LookupTable performance for large batch sizes | |||
2017-03-13 | change lookup table sort | Jeff Johnson | |
2017-03-06 | Improve precision testing | Gregory Chanan | |
1) In cases where tests were failing with some regularity (SmoothL1, l1cost, mse, SoftShrink-backward) scale error bounds by (absolute) value being tested. 2) Fix some spacing issues in error messages. | |||
2017-02-22 | Merge pull request #447 from gchanan/accreal | Soumith Chintala | |
Remove accreal typedef because it is defined multiple times | |||
2017-02-22 | Remove accreal typedef because it is defined multiple times | Gregory Chanan | |
with nn. | |||
2017-02-21 | Merge pull request #446 from lvdmaaten/master | Soumith Chintala | |
[DPT] Add option for synchronous copy of model to GPUs | |||
2017-02-21 | [DPT] Add option for synchronous copy of model to GPUs | Laurens van der Maaten | |
2017-02-21 | Merge pull request #418 from ruotianluo/adaptiveAverage | Soumith Chintala | |
Add SpatialAdaptiveAveragePooling. | |||
2017-02-21 | Merge pull request #434 from bottler/master | Soumith Chintala | |
VolumetricFractionalMaxPooling like spatial | |||
2017-02-21 | Merge pull request #442 from twitter-forks/half-fixes | Soumith Chintala | |
Convert real to accreal in libTHCUNN | |||
2017-02-20 | Merge pull request #445 from apaszke/nll_criterion | Soumith Chintala | |
Do SpatialClassNLLCriterion sizeAverage in a separate kernel | |||
2017-02-20 | Do SpatialClassNLLCriterion sizeAverage in a separate kernel | Adam Paszke | |
2017-02-18 | Merge pull request #444 from apaszke/fixes | Soumith Chintala | |
Improvements for spatial functions | |||
2017-02-18 | Use a more stable formula for spatial LogSoftMax | Adam Paszke | |
2017-02-18 | Add shape checks for SpatialClassNLLCriterion | Adam Paszke | |
2017-02-17 | Convert real to accreal in libTHCUNN | Pavan Yalamanchili | |
- This reverts commit 0d85922d116879448485ef88ae21e83a9255a0b0. - Includes fixes for TemporalRowConvolution | |||
2017-02-15 | add local | soumith | |
2017-02-15 | implementation of bias=False for VolConv.cu | Eli Stevens | |
2017-02-08 | Merge pull request #440 from gchanan/glugeneric | Soumith Chintala | |
Use THCTensor rather than THCudaTensor in GatedLinearUnit | |||
2017-02-08 | Use THCTensor rather than THCudaTensor in THCUNN.h definition of | Gregory Chanan | |
GatedLinearUnit. | |||
2017-02-03 | Merge pull request #438 from huihuifan/betterCudaGLU | Soumith Chintala | |
cuda implementation of Gated Linear Unit, fixed issues with genericiz… | |||
2017-02-03 | cuda implementation of Gated Linear Unit, fixed issues with genericization | Angela Fan | |
2017-02-02 | Merge pull request #437 from torch/revert-430-newCudaGLU | Soumith Chintala | |
Revert "cuda implementation of Gated Linear Unit, fixed issues with genericization" | |||
2017-02-02 | Revert "cuda implementation of Gated Linear Unit, fixed issues with ↵revert-430-newCudaGLU | Soumith Chintala | |
genericization" | |||
2017-02-02 | Merge pull request #430 from huihuifan/newCudaGLU | Soumith Chintala | |
cuda implementation of Gated Linear Unit, fixed issues with genericization | |||
2017-02-01 | VolumetricFractionalMaxPooling like spatial | jeremy | |
2017-01-31 | Merge pull request #433 from apaszke/unpooling_leak | Soumith Chintala | |
Fix memory leak in SpatialMaxUnpooling | |||
2017-01-31 | Fix memory leak in SpatialMaxUnpooling | Adam Paszke | |
2017-01-29 | Merge pull request #431 from apaszke/asserts | Soumith Chintala | |
Compile with asserts by default | |||
2017-01-29 | Compile with asserts by default | Adam Paszke | |
2017-01-27 | Added cunn support for TemporalRowConvolutionMM (#415) | Will Frey | |
* Added cunn TemporalRowConvolutionMM support | |||
2017-01-27 | cuda implementation of Gated Linear Unit, fixed issues with genericization | Angela Fan | |
2017-01-26 | Merge pull request #428 from colesbury/CMake | Soumith Chintala | |
Install THCUNN.h and generic/THCUNN.h | |||
2017-01-26 | Install THCUNN.h and generic/THCUNN.h | Sam Gross | |
The THCApply.cuh is moved to the .cu files so that THCUNN.h can be compiled by a standard C compiler. | |||
2017-01-26 | Merge pull request #427 from torch/revert-416-half-fixes | Soumith Chintala | |
Revert "Convert real to accreal in libTHCUNN" | |||
2017-01-26 | Revert "Convert real to accreal in libTHCUNN"revert-416-half-fixes | Soumith Chintala | |
2017-01-25 | Merge pull request #426 from torch/revert-421-cudaGLU | Soumith Chintala | |
Revert "cuda implementation of Gated Linear Unit" | |||
2017-01-25 | Revert "cuda implementation of Gated Linear Unit"revert-421-cudaGLU | Soumith Chintala | |