GitLab

Always match dims with the smaller dimension from onnxruntime. Retina net
is outputting the correct amount of data (300) but out of onnxruntime, the
output is much smaller (5).

Useful to get more insight into Onnxruntime. Allows us to reuse the accuracy checker code while also allowing us to capture Execution Provider output with the --ort_run and --ort_logging flags

Also added the --target flag as well to allow us to force using either a specific target for the accuracy checking. Originally this was defaulting to the GPU. This now allows us to use ref, fpga, etc to quickly change targets.

[Experimental] Update accuracy checker for tf support and map input dims (custom input shape) (#1514)

* update file reading function to fix external data loading

Stream sync changes and associated API level changes

Added an Accuracy checker to the tools directory.  Currently compares ONNX FP32 models against ORT CPUEP