TensorRT 6.0 support

This version adds updated support for TensorRT 6.0.

Added Arm NN TFLite target

This armnn_tflite target is similar to armnn_tf but instead uses the TensorFlow Lite parser API. In addition, it can now run the SSDMobileNet TFLite model.

Google Edge TPU and TensorFlow Lite Support

Release notes:

1. Added a Python-based TensorFlow Lite target; this is provided purely for development and analysis purposes as we have observed significant issues with performance between releases
2. Converted the fp32 MLMark reference TensorFlow models from the frozen graph (*.pb) to fp32 TensorFlow Lite *.tflite format (see target readme file)
3. Converted the fp32 MLMark reference TensorFlow models from the frozen graph (*.pb) to quantized int8 TensorFlow Lite *.tflite format (see target readme file)
4. Compiled the above int8 models using the Google Edge TPU compiler (see targetreadme file)
5. Added a google_tpu target for use with Google Edge TPU devices such as the Coral Dev board and the USB accelerator
6. Renamed armnn_ubuntu to armnn_tf to indicate the framework used within Arm NN.
7. Minor edits to readme files for informative purposes.

First GitHub Release

This is the first official release of EEMBC's MLMark benchmark.