Dwayne Robinson
6e4c534ce2
Relax tolerance slightly more for Intel after autopilot run
2021-12-02 19:42:31 -08:00
Dwayne Robinson
77e67a6de7
Add one more example line
2021-12-02 13:34:01 -08:00
Dwayne Robinson
ef7671b938
Comment out old lines
2021-12-02 13:30:34 -08:00
Dwayne Robinson
7a3abd863f
Update WinML model test tolerances for tiny_yolov2 and FNS_Candy
2021-12-02 00:48:54 -08:00
Tiago Koji Castro Shibata
20b9390d1d
Merged PR 6524907: Fix merge conflicts from public ORT to WindowsAI ORT
2021-10-01 22:47:52 +00:00
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
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
Ryan Lai
10102c09b6
Add better model test error messaging ( #7239 )
2021-04-05 14:59:19 -07:00
Justin Stoecker
af4e5c0c6e
Minor WinML model test skip name change
2021-02-17 14:27:58 -08:00
Justin Stoecker
1c72774232
Update a few WinML model test filters for DML
2021-02-09 10:23:57 -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
Ryan Lai
e40df385ba
Skipping even more x86 tests ( #5799 )
2020-11-15 20:52:26 -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
