GitLab

Throwing on these calls catches dynamic shape errors earlier rather than having to backpedal from a bad call

* fix parse_instancenorm to create broadcast and multibroadcast instructions with two dynamic shape arguments instead of 1.  Their make_op() functions don't support dynamic shapes when called with one input.  This caused an error when parsing an ONNX 3duunet model

* Use add_common_op() to create multibroadcast op.

* add verification and parsing test for instance_norm with dynamic input.  Parse test doesn't pass.

* fix for test; still doesn't pass

* another fix for test; still doesn't pass

* work in progress, instance_norm_dyn_batch_test works but instance_norm_test doesn't

* fix onnx instancenorm tests to match parser changes.  Passes all check tests

* Updated comments explaining usage of add_common_op()

* hand-merged conflicts with develop

* fix instance_norm_half_test after merge

* add Onnx test instance_norm_dyn_batch_half_test

* add shape test cases broadcast_1in_dyn_error and multibroadcast_1in_dyn_error_0

By converting to fp32 : fp16 3d-unet model accuracy comes out the same as FP32 accuracy.

By using reduce_sum method on Fp16 : accuracy comes out ~0.9% lower compared to fp32 while keeping entire model in fp16.

Move CI to support the rocm5.5 release

instancenorm parser always creates literal of type float which would fail in type check while creating binary ops if model is fp16.

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

* rename broadcast and multibroadcast output_lens attribute to out_lens attribute, and change tests and source code to reflect the same

* change the reshape attribute from dims to out_lens

* change transpose attribute's name from dims to perm to reflect better meaning

* use permutation instead of perm for transpose

clang formaating

* use dims instead of out_lens for reshape

clang formatting

* Load op when serializing

* Formatting

* Add missing clip field

* Use make_op almost everywhere

* Formatting

* More make ops for rnns

* Get rid of spaces

* Formatting

* Remove operators headers

* Formatting

* Remove unused op headers

* Increase line threshold

* Refactor onnx_parser class

* Formatting

* Add op_parser

* Formatting

* Remove old onnx drivers

* Use file GLOB

* Parse arg ops

* Formatting

* Add pooling

* Formatting

* Add parse_natchnorm

* Add more operators

* Formatting

* Add more operators

* Formatting

* Add more operators

* Formatting

* Add more operators

* Add rnn operators

* Formatting

* Fix tidy issues

* Formatting

* Add back missing param

* Formatting

* Fix shadow variable

* Fix shadow in declaration

* Make global constant

* Formatting

* Add generic op

* Formatting

* Add binary op

* Formatting

* Add variadiac op

* Formatting

* Remove unused fields and functions

* Set default values

* Formatting

* Remove unused member variable

* Add add literal overload

* Use info.add_literal

* Formatting

* Call add_instruction through info class

* Fix tidy issues

* Formatting
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>