Commit graph

147 commits

Author SHA1 Message Date
Sheil Kumar
bd5067a2ff
Cannot upgrade SDK version because winml_lib_telemetry pulls in SDK cppwinrt version (#7795)
* fix telemetry includes

* add dependencies

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2021-05-24 08:00:24 -07:00
Hariharan Seshadri
4b691a5c0d
Add ability for memory arenas to "shrink" periodically (#7284) 2021-05-08 07:53:21 -07:00
sumitsays
e344a583b0
updated sampleTolerance of model fp16_inception_v1 for GPU execution provider (#7533)
Co-authored-by: Sumit Agarwal <sumitagarwal@microsoft.com>
2021-05-03 12:08:31 -07:00
Sheil Kumar
8e3cdf0452
Use unicode apis for loadlibrary (#7523)
Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2021-05-03 07:24:40 -07:00
Ori Levari
dfca1a09d5
Add Thread Spinning Session Option in WinML (#7498)
Co-authored-by: Ori Levari <orlevari@microsoft.com>
2021-04-30 11:44:58 -07:00
Adrian Tsai
70e67ddd2b
Update DirectML version to 1.5.1 and enable ARM/ARM64 builds with DML (#7511)
* Update DirectML to version 1.5.1
* Enable --use_dml with ARM and ARM64
* Add ARM/ARM64 binaries to nuget packages
2021-04-30 00:49:30 -07:00
Changming Sun
1012535dab
Change onnxruntime::make_unique to std::make_unique (#7502)
1. Change onnxruntime::make_unique to std::make_unique
2. Add "-std=c++14" to ROCM EP's build flags.
2021-04-29 17:04:53 -07:00
Adrian Tsai
f13b378995
Re-disable tests (#7495) 2021-04-28 21:50:22 -07:00
sumitsays
d67c86265b
Enabled fp16-inception-v1 test (#7406)
Co-authored-by: Sumit Agarwal <sumitagarwal@microsoft.com>
2021-04-22 23:05:03 -07:00
Sheil Kumar
265db2ad96
Fix Microsoft.AI.MachineLearning .NET5 publishing and C# Store Release build (#7373)
* fix .net publishing

* make experimental api build with microsoft.ai.machinelearning.idl import

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2021-04-19 15:36:43 -07:00
Brian Martin
3eb2d349a6
fix typo in scenariotestscppwinrt.cpp (#7334)
the word is spelled, "resetting".
2021-04-14 08:26:55 -07:00
Sheil Kumar
b7c89ce78a
User/sheilk/add api usage telemetry (#7320)
* winml telemetry

* change name to ApiUsage

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2021-04-12 17:51:25 -07:00
Ryan Lai
10102c09b6
Add better model test error messaging (#7239) 2021-04-05 14:59:19 -07:00
Brian Martin
06df28748f
Change tabs to spaces in Windows.AI.MachineLearning.idl (#7088)
noticed this in a recent PR, this file has some tabs that should be spaces.
2021-03-22 09:23:18 -07:00
Ori Levari
783acb144f
Ignored return value SDL bug fix (#6451) 2021-03-16 15:00:08 -07:00
Justin Stoecker
af4e5c0c6e
Minor WinML model test skip name change 2021-02-17 14:27:58 -08:00
Sheil Kumar
87cb6fd495
Add LearningModelBuilder to WinML Experimental Namespace along with various Audio operators (#6623)
* model building

* fix build

* winml adapter model building api

* model building

* make build

* make build again

* add model building with audio op

* inplace and inorder fft

* add ifft

* works!

* cleanup

* add comments

* switch to iterative rather than recursive and use parallelization

* batched parallelization

* fft->dft

* cleanup

* window functions

* add melweightmatrix op

* updates to make spectrogram test work

* push latest

* add onesided

* cleanup

* Clean up building apis and fix mel

* cleanup

* cleanup

* naive stft

* fix test output

* middle c complete

* 3 tones

* cleanup

* signal def new line

* Add save functionality

* Perf improvements, 10x improvement

* cleanup

* use bitreverse lookup table for performance

* implement constant initializers for tensors

* small changes

* add matmul tests

* merge issues

* support add attribute

* add tests for double data type windowfunctions and minor cleanup

* stft onesided/and not tests

* cleanup

* cleanup

* clean up

* cleanup

* remove threading attribute

* forward declare orttypeinfo

* warnings

* fwd declare

* fix warnings

* 1 more warning

* remove saving to e drive...

* cleanup and fix stft test

* add opset picker

* small additions

* add onnxruntime tests

* add signed/unsigned

* fix warning

* fix warning

* finish onnxruntime tests

* make windows namespace build succeed

* add experimental flag

* add experimental api into nuget package

* add experimental api build flag and add to windows ai nuget package

* turn experimental for tests

* add minimum opset version to new experimental domain

* api cleanup

* disable ms experimental ops test when --ms_experimental is not enabled

* add macro behind flag

* remove unused x

* pr feedback

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2021-02-12 14:17:10 -08:00
Xiang Zhang
8502573125
fix CheckLearningModelPixelRange (#6632) 2021-02-10 10:23:54 -08:00
Justin Stoecker
1c72774232
Update a few WinML model test filters for DML 2021-02-09 10:23:57 -08:00
Ryan Lai
c7feb48083
Don't send out Runtime error telemetry when can't create LearningModelDevice on machine without hardware adapters (#6535)
* Checkoutpoint 1

* Remove global logruntime error telemetry. This isn't necessary and doesn't contain relevant information

* Make macro simpler

Co-authored-by: Ryan Lai <ryalai96@gamil.com>
2021-02-03 14:27:29 -08:00
Ori Levari
3a30ad7b57
handle hr error conditions (#6449)
Co-authored-by: Ori Levari <orlevari@microsoft.com>
2021-01-29 15:01:08 -08:00
Ori Levari
531eb064ab
fix sdl bugs for uninitialized variables and returns (#6450)
Co-authored-by: Ori Levari <orlevari@microsoft.com>
2021-01-29 15:00:44 -08:00
Ori Levari
76f5d9edc6
add explicit barriers for buffer overread and overrwrite (#6484)
Co-authored-by: Ori Levari <orlevari@microsoft.com>
2021-01-29 14:59:56 -08:00
Ori Levari
3b1227c5ce
SDL annotation fixes (#6448)
Co-authored-by: Ori Levari <orlevari@microsoft.com>
2021-01-28 22:34:10 -08:00
Ori Levari
21b4842c34
SDL fixes: add proper casts/format specifiers (#6446) 2021-01-28 22:33:04 -08:00
Xiang Zhang
ce46f37ff2
expose learningmodelpixelrange property (#5877) 2021-01-28 15:29:55 -08:00
Sheil Kumar
ea2b560055
Fix test breaks in Windows ingestion pipeline (#6476)
* fix various build breaks with Windows build

* fix runtime errors loading libraries from system32

* add build_inbox check to winml_test_common

* use raw string

* cleanup

* fix dll load

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2021-01-28 14:37:15 -08:00
Ori Levari
b6ac35fed3
use tickcount64 (#6447)
Co-authored-by: Ori Levari <orlevari@microsoft.com>
2021-01-27 15:52:35 -08:00
Sheil Kumar
d5f51c4033
Bug 31463811: Servicing: Redist (Nuget) conflicts with Microsoft.AI.MachineLearning starting 21H1+ (#6460)
* update load library code to have the fullly qualified path

* make it work for syswow32

* git Revert "make it work for syswow32"

This reverts commit b9f594341b7cf07241b18d0c376af905edcabae3.

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2021-01-27 12:25:03 -08:00
Sheil Kumar
0d20104a72
only build experimental api in redist (#6465)
Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2021-01-26 22:56:30 -08:00
Ori Levari
6507b4f818
Reintroduce experimental api changes and fix remote build break (#6385)
Co-authored-by: Ori Levari <orlevari@microsoft.com>
2021-01-22 15:15:53 -08:00
Ryan Lai
4db4982a5e
This added telemetry isn't needed (#6363) 2021-01-15 16:36:59 -08:00
Ryan Lai
961bb62ae4
Add create session to WinML telemetry to track WinML Usage (#6356) 2021-01-14 22:42:55 -08:00
Ryan Lai
0494a0f95f
Add ability to skip GPU tests based on GPU adapter name (#6198)
* Implement conversion from ortvalue to Itensor for string tensors and comparing sequence of maps of strings to floats

* PR comments

* Add ability to skip gpu tests according to adapter description

* spacing

* spacing

* spacing
2020-12-22 15:20:23 -08:00
Ryan Lai
21395f8e24
Implement comparing outputs that are sequence of maps of strings to floats (#6180)
* Implement conversion from ortvalue to Itensor for string tensors and comparing sequence of maps of strings to floats

* PR comments
2020-12-22 09:52:29 -08:00
Ryan Lai
1eb146f561
Implement conversion from ORT String to WinML Tensor String (#6097)
* Implement conversion from ort string to winml string

* NIT:comment
2020-12-10 17:47:50 -08:00
Ryan Lai
8bcb5fd119
Add skip test reason for onnx model zoo models and tier 2 models (#6081) 2020-12-10 14:41:17 -08:00
Ryan Lai
753af576c4
If building inbox, hook up winrt_activation_handler for WinML Tests (#6074)
* If building inbox, hook up winrt_activation_handler with what is already defined in in dllload.cpp

* Add base.h header

* Missed custom ops test
2020-12-10 14:41:01 -08:00
Sheil Kumar
00f43a3a68
add missing iclosable interface (#6036)
Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2020-12-04 13:21:03 -08:00
Xiang Zhang
b4e6cc59c7
skip the check for A channel (#5989) 2020-12-02 11:23:54 -08:00
Ryan Lai
897310f6fb
Add suspend handler with new telemetry event for UWP scenarios (#5907)
* Add suspend handler with new telemetry event

* Fix build warning

* Use cppwinrt from nuget

* Restore nuget packages

* add dependencies

* Add nuget_helpers

* Cleaned up

* Clean up

* Comment

* Add dependencies for the rest

* Remove unused line

* Update activation string

* PR comment to remove ALL
2020-12-01 20:26:18 -08:00
Sheil Kumar
84c1340f9b
Refactor implementation of Tensor<T> and underlying buffer stores to improve binary size and maintainability (#5836)
* refactor tensor buffers to make cleaner

* refactor to make tensor backing buffer implementation smaller and cleaner

* missed virtual on destructor

* remove unnecessary static_pointer_cast

* add string vector accessor

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2020-11-18 14:56:47 -08:00
Tiago Koji Castro Shibata
794e8479eb
Revert #5805 (#5823)
* Fix race condition in msbuild

* Revert "Named Dimension Override internals test and experimental API (#5805)"

This reverts commit 157d1844fb.
2020-11-16 17:05:28 -08:00
Sheil Kumar
671fa60327
Enable direct tensorization and detensorization to many buffers in WinML (#5791)
* switch to work PC

* back with iterable of buffers

* add raw api tests

* tensorization

* last test

* all tests pass!

* small cleanup

* whitespace

* newline

* whitespace

* refactor common code into DisjointBufferHelpers

* remove unused file

* warning

* skip gpu tests when hardware not available

* Add error condition when createreference is invoked

* add null check to cretereference

* uncomment out check

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2020-11-16 10:06:22 -08:00
Ryan Lai
e40df385ba
Skipping even more x86 tests (#5799) 2020-11-15 20:52:26 -08:00
Ori Levari
157d1844fb
Named Dimension Override internals test and experimental API (#5805) 2020-11-13 21:21:11 -08:00
Ryan Lai
697e8faa9e
Skip failing x86 winml tests and update testData environment variable path mechanism (#5719)
* Skip failing x86 winml tests

* fix gpt2 rename typo

* there are actually 2 gpt model tests
2020-11-06 13:59:29 -08:00
Ryan Lai
bbfd914d72
Skip new model test additions (#5611) 2020-10-28 13:27:49 -07:00
Ryan Lai
98538580c8
give more tolerance to DirectML runs (#5564) 2020-10-21 23:14:51 -07:00
Ryan Lai
f207f0bf5e
Add WinML Model testing (#5417)
* Model test start with float

* Clean up code and add environment variable detection

* Move into namespace

* PR comments

* Fix linker errors in latest merge to master and also fix warning

* add skipping model test mechanism

* Return std::string instead of writing to buffer

* Address case where env variable is larger than max_path

* use const static string for test reason

* Disable x86 tests and don't build if ort memory checker is enabled

* Add comment

* Add additional failing x86 tests and ifdef for checking fo rx86 build

* PR comments
2020-10-15 19:04:12 -07:00