* Make quantization support GPT2 past state
* Make OpTester to be able to generate reference outputs with a model. With it, there is no need to compute outputs manually, which are impossible for some cases.
Fix 3 bugs:
node names duplicate in calibration augment_graph if the name of node to quantize is empty.
If output nodes are quantized, output value are quantized and not dequantized back
Gather with data type int64 should not be quantized
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 calibration tool
* add model for e2e example
* format readme
* some more formatting updates
* plus a few more updates
* plus review comments
* plus updates
* more updates
* Move quantization tool from onnx to onnxruntime
* Fix some issues
* Use u8_s8 for asymmetric mode and u8_u8 for symmetric mode irrespective of whether inputs are initializers or from previous
* Address PR comments
* Fix error message formatting
* Separate static/dynamic and quantization mode
