saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-01 03:45:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Relax tolerance slightly more for Intel after autopilot run

Browse source
This commit is contained in:
Dwayne Robinson 2021-12-02 19:42:31 -08:00
parent 77e67a6de7
commit 6e4c534ce2
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
winml/test/model/skip_model_tests.h
View file

@ -145,7 +145,7 @@ std::unordered_map<std::string, double> sampleTolerancePerTests(
{
{"fp16_inception_v1_opset7_GPU", 0.005},
{"fp16_inception_v1_opset8_GPU", 0.005},
{"candy_opset9_GPU", 0.00121000}, // Intel(R) UHD Graphics 630 (29.20.100.9020) AP machine has inaccurate GPU results for FNS Candy opset 9 https://microsoft.visualstudio.com/OS/_workitems/edit/30696168/
{"candy_opset9_GPU", 0.00150000}, // Intel(R) UHD Graphics 630 (29.20.100.9020) AP machine has inaccurate GPU results for FNS Candy opset 9 https://microsoft.visualstudio.com/OS/_workitems/edit/30696168/
{"fp16_tiny_yolov2_opset8_GPU", 0.109000}, // Intel(R) UHD Graphics 630 (29.20.100.9020) AP machine has inaccurate GPU results for FNS Candy opset 9 https://microsoft.visualstudio.com/OS/_workitems/edit/30696168/
}
);