Sumit Agarwal 3f43a84e10 Merged PR 6093117: Fix test_DynamicQuantizedLinear_max_adjusted_expanded by allowing Identity operator to run on non-float inputs ... Motivation: As part of the OnnxConformance Backend tests, DynamicQuantizedLinear_max_adjusted_expanded is failing. Root Cause: - The test model has `Identity` operator as one of the node. The input of this node is of non-float data type. - In DML, `Identity` operator is registered as operator which requires floating input. - As per `DirectMLSchema.h`, support for non-float input has been added for `Identity` operator in DML but the same has not been reflected in the `OperatorRegistration.cpp`. Changes: - Removed all traces of the requiresFloatFormatsForGraph flag from it's definition and usage. This flag was only used for Identity and it's related operator. - Added null check for the graphOutput nodeArg in GraphDescBuilder.cpp to stop the crash of the test. Related work items: #33076298		2021-05-28 17:44:37 +00:00
..
adapter	Merged PR 6093117: Fix test_DynamicQuantizedLinear_max_adjusted_expanded by allowing Identity operator to run on non-float inputs	2021-05-28 17:44:37 +00:00
api	Add Thread Spinning Session Option in WinML (#7498)	2021-04-30 11:44:58 -07:00
dll	Add LearningModelBuilder to WinML Experimental Namespace along with various Audio operators (#6623)	2021-02-12 14:17:10 -08:00
lib	Cannot upgrade SDK version because winml_lib_telemetry pulls in SDK cppwinrt version (#7795)	2021-05-24 08:00:24 -07:00
test	updated sampleTolerance of model fp16_inception_v1 for GPU execution provider (#7533)	2021-05-03 12:08:31 -07:00