onnxruntime/onnxruntime
Vincent Wang a6e219deff
Pass Model Path to TensorProtoToMLValue from Constant Folding for External Inputs (#5000)
* Don't constant fold external inputs.

* pass model_path to TensorProtoToMLValue

Co-authored-by: Vincent Wang <weicwang@microsoft.com>
2020-09-02 21:54:40 +08:00
..
contrib_ops Use raw attention mask in BERT related fusions (#4889) 2020-09-01 13:22:20 -07:00
core Pass Model Path to TensorProtoToMLValue from Constant Folding for External Inputs (#5000) 2020-09-02 21:54:40 +08:00
featurizers_ops/cpu
gsl
python Remove public default ctor in PyInferenceSession and replace it with a protected ctor (#4990) 2020-09-01 17:10:36 -07:00
test Pass Model Path to TensorProtoToMLValue from Constant Folding for External Inputs (#5000) 2020-09-02 21:54:40 +08:00
tool/etw Add option ORT_NO_EXCEPTIONS to disable most exception/throw in /onnxruntime/ (#4894) 2020-08-28 23:03:51 -07:00
.style.yapf
__init__.py Add new PytTrch front-end (#4815) 2020-08-17 09:45:25 -07:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings