Chi Lo 8c3b59a026 Quantization calibration refactor (#6893) ... * Code refactor * Modify code to tackle OOM when calibrating on larget dataset * Fix mismatch issue when setting keepdims on ReduceMin/ReduceMax * Add COCO val 2017 annotation * Fix mismatch issue when setting keepdims on ReduceMin/ReduceMax * Fix bug of "No module named:onnxruntime.quantization.CalTableFlatBuffers" * Check and install flatbuffers module * Add script to donwload coco dataset image and refactor example * Fix bug of "No module named:onnxruntime.quantization.CalTableFlatBuffers" * Add CalTableFaltBuffers as module * Remove annotation, user can download by themselves. * Uncommet code * Add back instances_val2017.json * Make sure flatbuffers installed when ORT is installed * Refactor code to call coco api * Enable FP16 for example		2021-03-19 01:09:11 -07:00
..
featurizer_ops	Update data_frame_tool to latest (#3919)	2020-05-18 21:13:56 -07:00
quantization	Quantization calibration refactor (#6893)	2021-03-19 01:09:11 -07:00
tensorrt/perf	Setup perf in docker and add features (#6582)	2021-02-25 09:31:03 -08:00
transformers	Support HuggingFace Models Converted From tf2onnx in Python Script (#6985)	2021-03-17 15:33:57 -07:00
__init__.py	Enable running PEP8 on python scripts using flake8 (#3928)	2020-05-15 07:15:06 +10:00
onnxruntime_test.py	Liqun/speech model loop to scan (#6070)	2021-01-05 15:15:23 -08:00
symbolic_shape_infer.py	Support symbolic shape infer in transformers tool (#6899)	2021-03-10 21:37:12 -08:00