* Fixed two issues in symbolic_shape_infer script
This change addressed #3293
There were two issues in the script:
* We need to handle a special case for infer_Reshape, where input_shape
is empty and target shape_value is [-1]. In such case, we need to
get sympy data for the output dim (or create one if it doesn't exist).
* We need to update computed dims for newly-created shape for Range op
* also call _update_computed_dims for _infer_Expand
addressed CR feedback
* added ai.onnx into opset list
* instead of manipulating _infer_Reshape, call _update_computed_dims
from _infer_Expand to update newly-computed dims
Implement pipeline event generator with OneFWOneBW schedule in timeline. Each stage of pipeline contains FW and BW of a subset of the model and are scheduled in one worker thread for each microbatch.
* Enable sequence of tensor
* add tests
* small updates
* There should only be 2 elements returned
* CR feedback, and another 6->2 check update in the test.
* missing semicolon...
* Add explicit to constructor taking pointer paramter
Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
* Implement operator[] for TArray and simplify the code.
* fix a build error.
* add a constructor with std::vector input
* fix build error
* update based on code review feedback
Co-authored-by: Weixing Zhang <wezhan@microsoft.com>
Update ReformatSourcePython.bat to use YAPF to format python code, and add onnxruntime\test directory to be formatted.
Add onnxruntime\.style.yapf for configuration. The style is based on google, except max column width 120.
Format python scripts using ReformatSourcePython.bat.
* Add notebook for bert squad model exported by python 1.4
* update bert performance test tool:
(1) set OpenMP environment variable before importing onnxruntime.
(2) launch new process for each test.
* Add notebook
Reduce combinations in perf test
* update readme
* fix quote
* Allow test multiple batch_size
* Add latency percentile
* Add warm up run
Reset logger for notebook
* refine default settings to test for cpu/gpu
* Add script to dump machine info
* Add notebooks for PyTorch SQuAD model GPU and CPU inference
* Update machineinfo.py: add license header; format by yapf
* Do not reset log handler. Skip adding handler if existed.
* Add comments about GPU result diff.
Filter rows of batch set to keep only one setting.
* update according to review feedback
* Download script from master branch
* Add notebook for bert model exported by keras2onnx
* format columns in result table
* re-run and update notebook
