* Libnd4j: Add broadcastable elementwise power derivative #7461 first step of Pow_bp operation implementation
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* Libnd4j: Add broadcastable elementwise power derivative #7461 some corrections of calculation steps
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* Libnd4j: Add broadcastable elementwise power derivative #7461 some bug fixes, the PowDerevative op made broadcastable, add the raw tests for op, need refactoring to use broadcast ops
* Libnd4j: Add broadcastable elementwise power derivative #7461 fixed several bugs add broadcast support and tests, need to fix scalar+array and array+scalar
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* Libnd4j: Add broadcastable elementwise power derivative #7461 fixed bugs for scalar inputs, fixed multinomial tests, added tests
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* Libnd4j: Add broadcastable elementwise power derivative #7461 fised bugs for different shapes support, tests updated
* Libnd4j: Add broadcastable elementwise power derivative #7461 applied all possible variants via tiled arrays, add support of broadcast for Pow and PowDerivative ops, covered by tests, before review have to be replaced tiled implementation by applyTrueBroadcast
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* Libnd4j: Add broadcastable elementwise power derivative #7461 replaced tile by broadcast implementation, fixed issue with negative x input, corrected tests, need additional testing
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* Libnd4j: Add broadcastable elementwise power derivative #7461 added and corrected test cases, corrected implementation need review
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* Libnd4j: Add broadcastable elementwise power derivative #7461 code clean up
* Libnd4j: Add broadcastable elementwise power derivative #7461 code clean up, removed some tests, add tests with scalar
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* Libnd4j: Add broadcastable elementwise power derivative #7461 code improvement and clean up, split tests
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* Libnd4j: Add broadcastable elementwise power derivative #7461 some code clean up
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* Libnd4j: Add broadcastable elementwise power derivative replace __isnanf by internal realization
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* pow_bp wrapper
* Fixed PowBp wrapper
* Tests added
* Test fixed
* Fix return type
* Disable powBp usage
* Pow backprop changed
Co-authored-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
* libnd4j: Multinomial op #8570 first raw step of multinomial random data generator implementation
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op #8570 next step of multinomial random categories generator implementation on both cpu and cuda, need corrections and code clean up before review and testing
* libnd4j: Multinomial op #8570 code clean up and fixed issues data selecting, moved from coords to tads
* libnd4j: Multinomial op #8570 fixed cuda build add reference for math materials that was used for implementation
* libnd4j: Multinomial op #8570 fixed several bugs, added several tests and improved cuda version. current implementation works, need testing of reproduction with the same seed
* libnd4j: Multinomial op #8570 fixes and optimization after discussion in both cuda and cpu
* libnd4j: Multinomial op #8570 add corrections after review, removed tads, replace 2D parallel loop by 3D
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op fixed declaration and add tests need discussion
* libnd4j: Multinomial op fix in test
* libnd4j: Multinomial op corrected behavior to get reproducible results, fixed issue in uniform value getting, tests added, need cuda review and cuda testing
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op fixed indexing on uniform calculation
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op some corrections in max min declaration
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op fixed index calculation, added rewind, corrected input declaration, added stats tests, both cuda and cpu. cuda need testing
* libnd4j: Multinomial op fixed bugs on cuda nad cpu. need review
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op corrected tests to handle different orders
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op some improvements after code review
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op more corrections after review
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op fixed seed usage, update tests, fixed cuda based on comments, fixed bug of rewind, removed one behavior, minor corrections.
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op minor corrections
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op rise the bound of fluctuation for random cases
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: Multinomial op modified operation inputs and update implementation and tests on both cpu and cuda
* libnd4j: Multinomial op corrected data types according ops.proto
Co-authored-by: raver119 <raver119@gmail.com>
* libnd4j: RgbToYuv and YuvToRgb, both implementations for both cpu and cuda. Need adding tests and review
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: RgbToYuv and YuvToRgb, replace coords method on Tad in both cpu and cuda, add tests, fixed bugs
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: RgbToYuv and YuvToRgb minor corrections
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: RgbToYuv and YuvToRgb corrections to use operations in-place
* libnd4j: RgbToGrayscale op #8536 - raw implementation in user branch, need checks for integration and adding other orders
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: RgbToGrayscale op #8536 next step of merging images
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: RgbToGrayscale op #8536, Revert merge of hsv_to_rgb and rgb_to_hsv as cause conflicts in naming need refactoring before merge, implementation of rbg_to_grs added
* libnd4j: RgbToGrayscale op #8536 imlementation and conflict resolve
* libnd4j: RgbToGrayscale op #8536 merged operations with images into image, renamed methods and files
* libnd4j: RgbToGrayscale op #8536 added test for rgbToGrayScale, need clarification and fixed tests case run
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* libnd4j: RgbToGrayscale op #8536 bug fixing and need review
* libnd4j: RgbToGrayscale op #8536 some additional corrections after review
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* - minor corrections in rgbToGrs test1
Signed-off-by: Yurii <iuriish@yahoo.com>
* libnd4j: RgbToGrayscale op #8536, corrected tests and rbf_to_grs, fixed problems, refactoring, need review
* libnd4j: RgbToGrayscale op #8536 fix for 'f' order in rgbToGrs
* libnd4j: RgbToGrayscale op #8536 fixed several bugs with dimC, test case refactoring and improve
Signed-off-by: Oleg <oleg.semeniv@gmail.com>
* - add cuda kernel for rgbToGrs op
Signed-off-by: Yurii <iuriish@yahoo.com>
* - fix linkage errors
Signed-off-by: Yurii <iuriish@yahoo.com>
Co-authored-by: Yurii Shyrma <iuriish@yahoo.com>
* Added infrastructure for implementation op lu for both cuda and cpu platforms.
* Added implementation of helpers with lu op.
Signed-off-by: shugeo <sgazeos@gmail.com>
* Refactored LU decomposition to use vector of permutations instead.
* Refactored helpers for lu op.
* Fixed crash with determinant op.
* Refactored cpu LU op heleper.
* Added implementation for lu op.
Signed-off-by: shugeo <sgazeos@gmail.com>
* Fixed issue with argmax on column.
* Added multithreaded behaviour for lu op helper.
* Fixed multithreaded cpu implementation helpers for lu op.
* Added cuda implementation for lu op helper.
* Finished lu helper implementation for cuda platform.
* Eliminated waste prints and comments.
* Fixed race condition and multithreading issues.
* Fixed memory leak with shape construction.
* Corrected test for lu op to avoid near zero elements on the main diagonal."
Signed-off-by: shugeo <sgazeos@gmail.com>
* Improved test for adjust_constast op.
Signed-off-by: shugeo <sgazeos@gmail.com>
* Fixed issues with cuda implementation of resize_bicubic helpers.
Signed-off-by: shugeo <sgazeos@gmail.com>
* CUDA implementation for hsv_to_rgb and rgb_to_hsv
Signed-off-by: raver119 <raver119@gmail.com>
* hsv_to_rgb and rgb_to_hsv operations
Test coverage: c order 1d, 2d, 3d array
Signed-off-by: Abdelrauf <rauf@konduit.ai>
* Index check
Signed-off-by: Abdelrauf <rauf@konduit.ai>
* Suppress Msvc floating point errors
Signed-off-by: Abdelrauf <rauf@konduit.ai>
* Added Index Check for adjust_saturation and adjust_hue
Signed-off-by: Abdelrauf <rauf@konduit.ai>
* minor fix
Signed-off-by: raver119 <raver119@gmail.com>
* Fixes missed Msvc floating narrowing errors
Signed-off-by: Abdelrauf <rauf@konduit.ai>
* - add possibility of passing scalar-array as input parameter for scale factor in adjust hue/contrast/saturation ops
- correct typo in function which calculates regularized incomplete beta integral
Signed-off-by: Yurii <iuriish@yahoo.com>
* - fix bug in betainc cuda kernel
Signed-off-by: Yurii <iuriish@yahoo.com>
* - start working on implementation of digamma function
Signed-off-by: Yurii <iuriish@yahoo.com>
* - further work on digamma function (cpu)
Signed-off-by: Yurii <iuriish@yahoo.com>
* - testing and fixing bugs in digamma op
Signed-off-by: Yurii <iuriish@yahoo.com>
* - make correction n cuda kernel for polyGamma
Signed-off-by: Yurii <iuriish@yahoo.com>
* - remove unnecessary stuff from betaInc cuda kernel
Signed-off-by: Yurii <iuriish@yahoo.com>
* - resolve conflicts in DeclarableOpsTests3.cpp after master branch has been merged
Signed-off-by: Yurii <iuriish@yahoo.com>
* - restore id number of Not opertion in legacy_ops.h
Signed-off-by: Yurii <iuriish@yahoo.com>
* - correct padding calculation in mkl dnn conv1d causal
Signed-off-by: Yurii <iuriish@yahoo.com>
* restore empty check in adjust_contrast_v2
Signed-off-by: raver119 <raver119@gmail.com>
* - add causal mode of padding to convolutions
Signed-off-by: Yurii <iuriish@yahoo.com>
* - add additional tests for causal conv1d
Signed-off-by: Yurii <iuriish@yahoo.com>
* - add causal mode for cuda conv kernels
Signed-off-by: Yurii <iuriish@yahoo.com>
* Java side of Conv1D changes
Signed-off-by: raver119 <raver119@gmail.com>
* Add Conv1DDerivative op
Signed-off-by: Alex Black <blacka101@gmail.com>
* Causal Conv1D gradient checks
Signed-off-by: Alex Black <blacka101@gmail.com>
* Tweaks
Signed-off-by: Alex Black <blacka101@gmail.com>
* - add causal padding mode to conv2d_bp
Signed-off-by: Yurii <iuriish@yahoo.com>
* More thorough causal conv1d tests
Signed-off-by: Alex Black <blacka101@gmail.com>
* Implementation for non_max_suppression_v3 was added. Initial version
* Added check for overcome threshold.
* Added definition for V3 method.
* java remapping for NonMaxSuppressionV3
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed proporly processing of an empty output and test.
* Refactored op to less threshold data to float.
* Implemented cuda-based helper for non_max_suppression_v3 op.
* Fixed fake_quant_with_min_max_vars op.
* Fixed tests with float numbers.
* - assert now stops execution
- sortByKey/sortByValue now have input validation
Signed-off-by: raver119 <raver119@gmail.com>
* missing var
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed proper processing for zero max_size inputs.
* Refactored kernel callers.
* Fixed return statement for logdet op helper.
* Refactored unsorted segment SqrtN op.
* get back 8 tail bytes on CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* Refactored segment prod ops and helpers for cuda and tests.
* Additional test.
* CudaWorkspace tests updated for 8 tail bytes
Signed-off-by: raver119 <raver119@gmail.com>
* special atomic test
Signed-off-by: raver119 <raver119@gmail.com>
* atomicMul/atomicDiv fix for 16bit values
Signed-off-by: raver119 <raver119@gmail.com>
* Eliminated waste prints.
* - create op
- skip exec for empty inputs for non_max_suppression
- EmptyHandling idea
Signed-off-by: raver119 <raver119@gmail.com>
* Create op and mapping for it
Signed-off-by: raver119 <raver119@gmail.com>
* Added implementation files for image_resize and resize_bicubic ops.
* Image resize and image.resize_bicubic ops implementation. Initial revision.
* Minor fix
* Some TF imports disabled.
* Finished with infrastructure development for image.resize_bilinear op and image_resizo op implementation.
* Refactored resize methods.
* Added processing for Mitchelcubic algorithm.
* adjust_contrast
* Small fix for TF import expected value loading when variable name starts with the test name
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tests
* Tests added.
* Removed tf names absent in mapping.
* Some fixes.
* Small fixes
* Minor change
* Some failing tests.
* Disable failed test
* Ignore some tests
* Fix import class mapping
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix float property mapping (flatbuffers)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Override equality function for model 'dropout'
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fail tests
* Failed tests ignored temporarily.
* Minor fixes
* Small fix
* Conflict resolved
* Default implementations of tensorflowName and onnxName
* one range test
Signed-off-by: raver119 <raver119@gmail.com>
* few Context convenience singatures
Signed-off-by: raver119 <raver119@gmail.com>
* one more range test
Signed-off-by: raver119 <raver119@gmail.com>
* "range" "fix"
Signed-off-by: raver119 <raver119@gmail.com>
* adjuct_contrast_v2 now allows scale factor to be provided via input_variable
Signed-off-by: raver119 <raver119@gmail.com>
* adjust_contrast now allows scale factor as variable too
Signed-off-by: raver119 <raver119@gmail.com>
* bitcast shape tests
Signed-off-by: raver119 <raver119@gmail.com>
* BitCast import dtype added
Signed-off-by: raver119 <raver119@gmail.com>
* few more BitCast signatures
Signed-off-by: raver119 <raver119@gmail.com>
* Corrected randomuniform declaration.
* Refactored uniform distribution for both cuda and cpu platforms.
* Refactored uniform distribution and tests.
* Fixed type usage with indices.
* Refactored uniform distribution implementation and tests to full conform with TF implementation.
* Refactored gamma function to use type util method.
* Copyright changes and fixes with ConstantHelper.
* Added error checking on allocate cuda device memory and operations.
* Added implementation for random_gamma op.
* Added implementation for random_poisson op and support classes.
* Added helpers for random_poisson and random_gamma ops.
* Implementation of random_poisson. The first working edition.
* Implementation of random_poisson. Parallelized working edition.
* Implementation of random_gamma. Parallelized working edition with alpha only.
* Added cuda implementation for helper of poisson distribution.
* Corrected shape calculation with random_gamma and tests.
* Finished cpu implementation for gamma distribution.
* Finished cuda implementation for random_gamma op.
* Refactored cpu helpers for random_gamma and random_poisson ops.
* Refactored cuda helpers for gamma and poisson distribution.
* Refactored cuda helper for gamma distribution.
* Refactored cpu helper for random_poisson op.
* Refactored cpu helper for random_gamma op.
* - provide possibility to pass axis as last input array in concat op
- corrcect sumation in bias_add_bp op for NHWC case
Signed-off-by: Yurii <iuriish@yahoo.com>
* - write code for deconv2d op based on mkl dnn api
* no unsafe math
Signed-off-by: raver119 <raver119@gmail.com>
* no unsafe math
Signed-off-by: raver119 <raver119@gmail.com>
* - get rid of e<> and p<> methods in svd helper
Signed-off-by: Yurii <iuriish@yahoo.com>
* - provide mkl api support for deconvolution 3d
Signed-off-by: Yurii <iuriish@yahoo.com>
* - write deconv2d_bp based on mkl api
Signed-off-by: Yurii <iuriish@yahoo.com>
* - write deconv3d_bp based on mkl api
Signed-off-by: Yurii <iuriish@yahoo.com>
* - testing and fixing deconv based on mkl api
Signed-off-by: Yurii <iuriish@yahoo.com>
* - remove dilation form conv2d/3d mkl
Signed-off-by: Yurii <iuriish@yahoo.com>
* - minor changes
Signed-off-by: Yurii <iuriish@yahoo.com>
* - further corrections of deconv ops based on mkl dnn api
Signed-off-by: Yurii <iuriish@yahoo.com>
* - provide deconv2d_tf based on mkl dnn api
Signed-off-by: Yurii <iuriish@yahoo.com>
* - add minor corrections required by reviewer
Signed-off-by: Yurii <iuriish@yahoo.com>
* Added non_max_suppression_overlaps op and tests.
* Refactored implementation of non_max_suppression_overlaps.
* Refactoring of implementation of non_max_suppression_overlaps op.
* Refactoring of implementation of non_max_suppression op.
* Fixed portion error.
* Added cuda frontends for image suppression ops.
* Eliminated crash with cuda arch on image.non_max_suppression_overlaps op.
* Improved implementation of image_suppression helper for cpu platform.
* The generic approach of non_max_suppression_overlaps op helper with cuda platform.
* Working cuda implementation of helper non_max_suppression_overlaps op.
* Eliminated waste comments.
* Improved implementations for both platforms
* Refactored cuda implementation of image.non_max_suppression_overlaps op helper.
* Improved cuda implementation of non_max_suppression op helper.
* Refactored cuda implementation of image.non_max_suppression_overlaps op helper.
* Improved cuda implementation of image.non_max_suppression_overlaps op helper.
* Added modifications into cuda implementation for image suppression overlaps op.
* Correct queue emulation with cuda implementation of non_max_suppression_overlaps op.
* Prefinal stage of cuda implementation of non_max_suppression_overlaps.
* Worked cuda implementation of non_max_suppresion_overlaps helper.
* Fixed return to proper thread.
* Improvements for cuda implementation of image.non_max_suppression_overlaps op helper.
* Fixed implementation issues with non_max_suppression_overlaps on cuda platform.
* Fixed skip for non_max_suppression_overlaps on cuda platform.
* Finalize implementation of image_suppression helper and tests.
* Cosmetic changes only.
* - write code for new batchnorm backprop
Signed-off-by: Yurii <iuriish@yahoo.com>
* - testing batchnorm backprop
Signed-off-by: Yurii <iuriish@yahoo.com>
* - write code for batchnorm backprop based on mkl dnn api
Signed-off-by: Yurii <iuriish@yahoo.com>
* - testing and fixing bugs in batchnorm_bp mkl dnn
Signed-off-by: Yurii <iuriish@yahoo.com>
* - made corrections required by reviewer
Signed-off-by: Yurii <iuriish@yahoo.com>
* - change name in java wrapper for batchnorm op
Signed-off-by: Yurii <iuriish@yahoo.com>
* - profiling bias_add op
- add some docementation
Signed-off-by: Yurii <yurii@skymind.io>
* - minor change
Signed-off-by: Yurii <yurii@skymind.io>
* - provide addBias cuda kernel
Signed-off-by: Yurii <yurii@skymind.io>
* - improve shape::getIndexOfffset and change its signature
Signed-off-by: Yurii <yurii@skymind.io>
* - same as previous
Signed-off-by: Yurii <yurii@skymind.io>
* - improve and change signature in some shape:: stuff which has to do with calculation of offsets for array elements
Signed-off-by: Yurii <yurii@skymind.io>
* - minor changes in flatten
Signed-off-by: Yurii <shyrma@skymind.io>
* - add function shape::getIndexOffsetOrdered
Signed-off-by: Yurii <shyrma@skymind.io>
* - correct shape::getIndexOffsetOrdered()
Signed-off-by: Yurii <shyrma@skymind.io>
* - move getIndexOffsetOrdered to flatten.h header in order to isolate this function
Signed-off-by: Yurii <shyrma@skymind.io>
* Actualized doc to tnse ops.
* Added comments for dynamic_stitch op.
* Added comments to dynamic_stitch op implementation.
* Modified comment for unstack_list op.
* Added doc for space_to_depth and depth_to_space ops.
* Added doc for space_to_batch op.
* Enlarge test type for adjustSaturation.
* Added doc for runner.
* - documenting and profiling matrix_set_diag cuda kernel
Signed-off-by: Yurii <yurii@skymind.io>
* - correct formula of pnorm pooling in cuda 2d/3d kernels
- remove helper matrix_diag which duplicates work of helper matrix_set_diag
Signed-off-by: Yurii <yurii@skymind.io>
* - add one additional test for svd
* - provide float argument in eye op to be a type of output array
Signed-off-by: Yurii <yurii@skymind.io>
* - add cuda capability check to mmulHelper
Signed-off-by: Yurii <yurii@skymind.io>
* - make use another method for divice id evaluation
Signed-off-by: Yurii <yurii@skymind.io>
* Eye data type as T argument
Signed-off-by: raver119 <raver119@gmail.com>
* - start working on space_to_batch_nd
Signed-off-by: Yurii <yurii@skymind.io>
* - provide cpu helper for space_to_batch_nd op
Signed-off-by: Yurii <yurii@skymind.io>
* few typos fixed
Signed-off-by: raver119 <raver119@gmail.com>
* - add tests for space_to_batch and correct bugs
Signed-off-by: Yurii <yurii@skymind.io>
* - write cuda kernel for space_to_batch op
Signed-off-by: Yurii <yurii@skymind.io>
* - add order argument to shape::index2coords method in convolution cuda ops
Signed-off-by: Yurii <yurii@skymind.io>
* - restore some previous code
Signed-off-by: Yurii <yurii@skymind.io>
* old col2im kernel activated
Signed-off-by: raver119 <raver119@gmail.com>
* - change coords calculation in col2im kernel
Signed-off-by: Yurii <yurii@skymind.io>
* - restore old col2im kernel
Signed-off-by: Yurii <yurii@skymind.io>
* - add custom op for batch_to_space
Signed-off-by: Yurii <yurii@skymind.io>
* - provide cpu version for batch_to_space_nd op
Signed-off-by: Yurii <yurii@skymind.io>
* - provide cuda kernel for batch_to_space_nd op
Signed-off-by: Yurii <yurii@skymind.io>
* Added tests for get_seed/set_seed ops.
* Added missed tests for scatter_sub/mul/div ops.
* Added tests for hardsigmoid and hardsigmoid_bp.
* Added tests for hardtanh and hardtanh_bp ops.
* Added test for histogram op.
* Added tests for identity op.
* Refactored mergemaxindex op. Added tests for log1p,mergemaxindex, mod and mod_bp ops.
* Fixed tests for FloorDiv.
* Added test for rank op.
* Added tests for rationaltanh/rationaltanh_bp ops.
* Added tests for realdiv/realdiv_bp.
* Added tests for rectifiedtanh/_bp ops.
* Added tests for shapes_of op.
* Added tests for shapes_of op.
* Added tests for size op.
* Added tests for softplus/_bp ops.
* Added tests for softsign/_bp ops.
* Added tests for toggle_bits op. Fixed processing of OP_IMPL and so on defititions.
* Added test for truncatediv op.
* Added another test for truncatediv op.
* Added another test for histogram.
* Added tests for unstack_list op.
* Refactored to_int32/uint32/float16/float32/double/int64/uint64 ops and tests.
* Refactored mergemaxindex op helper for cuda platform and tests.
* Fixed cuda kernel for histogram op helper.
* Refactor skipgram to avoid early buffers shift.
* Fixed check up with non_max_suppression op cuda helper. Added cuda kernel implementation for skipgram op helpers.
* Added implementation of skipgram op helper for cuda platform. Working revision
* Fixed mergeMaxIndex kernel and move it to separate source file.
Oleh
shugeo
raver119
Abdelrauf
Yurii Shyrma
Alex Black
Alexander Stoyakin
Yurii Shyrma