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

github.com/soumith/cudnn.torch.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2016-06-04Merge pull request #169 from SeanNaren/R5R5Soumith Chintala
Fixed error with batchFirst assertion
2016-05-26readme changeSoumith Chintala
2016-05-22Merge pull request #188 from szagoruyko/R5Sergey Zagoruyko
Fix avg pooling back-compatibility
2016-05-22add avg pooling back compat testSergey Zagoruyko
2016-05-22Revert "R5 initial port"Sergey Zagoruyko
This reverts commit ee6a36f0a366db777308b3bd60021d917761c758.
2016-05-17Merge pull request #184 from borisfom/R5_upSoumith Chintala
fix for V5 GA RNN APIs
2016-05-17fix for V5 GA RNN APIsNatalia Gimelshein
2016-05-17Merge pull request #183 from soumith/R5_Soumith Chintala
cudnn r5 final version checks
2016-05-17cudnn r5 final version checkssoumith
2016-04-29Revert "Added extracting of bias and weights of each layer"SeanNaren
This reverts commit b71a40186b5dec9ac18097663409c4098ea660d7.
2016-04-28Added extracting of bias and weights of each layerSeanNaren
2016-04-25Do not reset dropout descriptor if sequence length changesngimel
2016-04-23Merge pull request #171 from szagoruyko/R5-gradInput-moveSergey Zagoruyko
[R5] Move gradInput:resizeAs(input) everywhere
2016-04-20move gradInput resize to updateGradInputSergey Zagoruyko
2016-04-20Updated assertion for accGradParamsSeanNaren
2016-04-20Removed x calculations, updated makeContiguous functionSeanNaren
2016-04-20Updated gradOutput assertionSeanNaren
2016-04-19Fixed error with batchFirst assertionSeanNaren
2016-04-18Merge pull request #168 from borisfom/R5-intSoumith Chintala
Rebased the rest of R5 changes. Added more RNN modules.
2016-04-18Added tests, modified README and added RNN modulesSeanNaren
2016-04-18Add utility functions and correct tensor dimensions.Anthony Sandrin
Tensor dimensions needed to be reversed since RNN function expect stride 1 in the first dimension. Remove experimental RNN scripts. Make inputSize a parameter to the RNN layer and use strings for enum values. * add missing cutorch.sychronize() to SpatialConvolution benchmark * rename bench to benchSpatial * add benchVolumetric Set weights in __init() Remove unnecessary input argument to resetIODescriptors - added new convolution modes - cleaned up benchVolumetric Add missing synchronization test reverted to non-verbose and random optimizer Return output from RNN:updateOutput and zero cell output. cuDNN does not set cell output for RNN_RELU so the output was garbage. Check for nil cx/hx when not training. Correct self.RNNDesc to self.rnnDesc
2016-04-18Update TemporalConvolution.luangimel
Cleaner way of what fbesse was doing (thans fbesse!) and typo fix
2016-04-18Initial work for cudnn RNN api integrationAnthony Sandrin
Added cudnnFind auto-tuning Change RNN layer api and improve descriptor/tensor resizing conditions Implement updateGradInput and accGradParameters
2016-04-18Fixing backward pass of TemporalConvolutionFrederic Besse
2016-04-18R5 initial portBoris Fomitchev
Initial adjustment of internall cudnn calls Got rid of _v3 functions
2016-04-18Created branch for CUDNN5 workBoris Fomitchev
2016-04-16Merge pull request #167 from szagoruyko/bn-convert-2Soumith Chintala
[R5] cudnn.convert for BatchNorm
2016-04-16cudnn.convert for BNSergey Zagoruyko
2016-04-15add read for BatchNormSergey Zagoruyko
2016-04-14Merge pull request #165 from szagoruyko/r5-bnSergey Zagoruyko
[R5] Fix running_var in BatchNorm
2016-04-14fix running_var meaning in BNSergey Zagoruyko
2016-04-13R5 rebaseSergey Zagoruyko
2016-04-13Merge pull request #162 from szagoruyko/utils-clearSergey Zagoruyko
Use nn.utils.clear on temporary buffers
2016-04-11Merge pull request #163 from hughperkins/notes-on-benchmark-fastestSoumith Chintala
add notes on benchmark and fastest
2016-04-11add notes on benchmark and fastestHugh Perkins
2016-04-08use nn.utils.clearSergey Zagoruyko
2016-03-31Merge pull request #158 from szagoruyko/error-handlingSoumith Chintala
Improve error handling
2016-03-30print function called on errorSergey Zagoruyko
2016-03-30Merge pull request #152 from gheinrich/fix-temporal-convolutionSoumith Chintala
Fix TemporalConvolution output size
2016-03-30Merge pull request #157 from szagoruyko/gradinput-init-fixSoumith Chintala
Move gradInput resize to updateGradInput (SpatialConvolution)
2016-03-30move gradInput resize to updateGradInputSergey Zagoruyko
2016-03-29Merge pull request #147 from lospooky/avgpooling-count_include_padSoumith Chintala
Fixed cudnn -> nn avg-pooling conversion
2016-03-29Fixed cudnn -> nn avg-pooling conversionSimone Cirillo
cudnn.convert now properly initializes nn.SpatialAveragePooling.count_include_pad
2016-03-25Fix TemporalConvolution output sizeGreg Heinrich
Issue seen in updateOutput() when batch size is decreasing (e.g. 256->128): ``` .../torch/install/share/lua/5.1/torch/Tensor.lua:462: Wrong size for view. Input size: 66060288. Output size: 128x256x1008x1 stack traceback: [C]: in function 'error' .../torch/install/share/lua/5.1/torch/Tensor.lua:462: in function 'view' ...orch/install/share/lua/5.1/cudnn/TemporalConvolution.lua:62: in function <...orch/install/share/lua/5.1/cudnn/TemporalConvolution.lua:54> ``` See new test cudnntest.TemporalConvolution_reduceBatchSize() for a repro. Calling a tensor's set() method without extra parameters but the requested storage causes the tensor to see a 1-D view of the full storage (not the associated tensor). For example: ``` th> x=torch.Tensor(10) [0.0001s] th> y=x:resize(5) [0.0001s] th> torch.Tensor():set(y:storage()):size() 10 [torch.LongStorage of size 1] [0.0002s] ``` Proposed fix is to specify the desired view through the optional parameters of the set() method.
2016-03-24Merge pull request #150 from szagoruyko/convert-fixesSoumith Chintala
Fix saving cudnn->nn converted models
2016-03-24fix conversion for saved cudnn->nnSergey Zagoruyko
2016-03-24Merge pull request #149 from borisfom/fullconvSoumith Chintala
fix failing SpatialFullConvolution test
2016-03-24fix failing SpatialFullConvolution testNatalia Gimelshein
2016-03-22Merge pull request #148 from szagoruyko/conv-pad-checkSoumith Chintala
Check if padW and padH exist in SpatialConvolution
2016-03-22check if padW and padH existSergey Zagoruyko
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-15 19:41:52 +0300