GitLab

* changed split_single_dyn_dim to add a get_tuple_element instruction
needed to access tuple type created by select_module
* dyn_test_runner changed to have offload_copy to false
* split_single_dyn_dim is not going to work with offload_copy unless we
make `load`, `copy_to_gpu` and `copy_from_gpu` handle dynamic shapes

Updated each source file in the repo with the existing license.

1. Previous implementation assumes inputs and outputs .pb files are ordered, but it is not the case. So, we should use the name of the tensors in the input/output .pb files to match the input and output in the onnx model. (This change applies to the BERT_Squad model)
2. When parsing a model with dynamic input shape, current implementation uses the default batch_size for the unknown dims, which can cause parsing error for some cases (e.g. mask_rcnn model). The solution is we first read an input to get the shape, then use these shapes to parse the onnx model.

* add python test runner

* fix review comments

* move test runner to the tools folder

* raise an error if some cases failed

* clang format

* fix review comments
Co-authored-by: Paul Fultz II <pfultz2@yahoo.com>
Co-authored-by: Chris Austen <causten@users.noreply.github.com>