Commit graph

12 commits

Author SHA1 Message Date
Paul McDaniel
301d407b39
Layer dev paulm (#2507)
* commetns for dml graph transformer
fixed ort value passing using the allocatir info

* fixed and coded maps and sequences across the abi

* cleaned up w4's
cleaned up the model info ABI
delayload directml.dll from winml

* cleaned up namepsace aliases.
renamed _winmla to winmla
this was good PR feedback from tiago a while back.
2019-11-27 15:50:49 -08:00
Ryan Lai
197fd9ea3d
Remove usage of IOBinding in WinML and use C_API Run method (#2504)
* remove usage of iobinding

* Change data structure to use vector of Ort::Values

* Polish bind input / output

* Use C APIrun method

* Update providers on evaluate getresults

* Remove run and IObinding interface from WinMLAdapter

* Remove use of IObinding

* bind unbound outputs code moved to learningmodelbinding

* clean up unneeded istensor adapter function

* Fix comment

* Check if session is closed before binding and clearing

* PR feedback
2019-11-27 15:31:30 -08:00
Paul McDaniel
c27f56c38e
Layer dev paulm (#2492)
* commetns for dml graph transformer
fixed ort value passing using the allocatir info

* fixed and coded maps and sequences across the abi
2019-11-26 18:53:08 -08:00
Paul McDaniel
974ee0b74b Checking in a staging checkpoint point so that Ryan can work with me in parrallel 2019-11-25 12:50:04 -08:00
Paul McDaniel
44a4fc0cc2 Moved SessionOptions over to the abi 2019-11-19 18:15:47 -08:00
Paul McDaniel
be37e4c225
Layer dev paulm (#2424)
* model moved over.
everything builds clean.
step !

* weak ref comment

* added a wrapper for RoGetActivationFactory to hook back into winml for creating winml objects.
fixes model load.

* fixed some lifetime management.
fixed the debug build.
squeezenet passes using winmlrunner for CPU and GPU

* PR feedback.
2019-11-18 11:07:54 -08:00
Paul McDaniel
5a1177acaa
Layer dev paulm (#2423)
* model moved over.
everything builds clean.
step !

* weak ref comment

* added a wrapper for RoGetActivationFactory to hook back into winml for creating winml objects.
fixes model load.

* fixed some lifetime management.
fixed the debug build.
squeezenet passes using winmlrunner for CPU and GPU
2019-11-18 09:51:39 -08:00
Paul McDaniel
5350abe19d
LearningModelSession is cleaned up to use the adapter, and parts of b… (#2382)
this is a big PR.    we are going to move it up to layer_dev , which is still a L3 so we are still safe to do work there agile.

we are going to move this into the L3 so that ryan can start doing intergration testing.   

we will pause for a full code review and integration test result prior to going into the L2.

>>>> raw comments from previous commits >>> 

* LearningModelSession is cleaned up to use the adapter, and parts of binding are.
* moved everything in the winmladapter
made it all nano-com using, WRL to construct objects in the ORT side.
base interfaces for everythign for winml to call
cleaned up a bunch of winml to use the base interfaces.
* more pieces
* GetData across the abi.
* renamed some namepsace
cleaned up OrtValue
cleaned up Tensor
cleaned up custom ops.
everything *but* learnignmodel should be clean
* make sure it's building.   winml.dll is still a monolith.
2019-11-14 17:44:07 -08:00
Paul McDaniel
5406801670
Task 23998197: add winml_lib_core into onnnxruntime.dll (#2368)
* Task 23998197: add winml_lib_core into onnnxruntime.dll

* PR feedback
build break on perf_test
2019-11-11 14:34:19 -08:00
Paul McDaniel
b6f5eef1d9 more snipping to get core into ort 2019-11-08 13:23:44 -08:00
Ryan Lai
444bfcc26e Initial changes for layering 2019-11-07 16:50:24 -08:00
Adrian Tsai
7390b64af5 Initial Commit 2019-11-07 11:51:44 -08:00