GitLab

Removes numpy dependency from test_gpu.py test and re-enables Python tests for Python 3.6.

The inaccuracy was caused by ONNX round requires nearest integer rounding for halway (0.5) cases.
std::round rounds away from zero, thus giving wrong results with halfway cases.
Replaced std::round with std::nearbyint which uses the correct rounding by default.

Disable python tests on Python 3.6 temporarily till we remove numpy dependencies from the tests using them.
Different versions of Python are compatible with different versions of numpy, so we need to remove numpy dependency.

Since opset version 18, the Split operator allows splitting into unevenly sized outputs when the split input is not present, and a num_outputs attribute has been introduced.

This sets up the virtual environments for running python onnx tests.
ctest's fixtures are used to ensure that the virtual environment is
set up before the tests are run.

Co-authored-by: Attila Dusnoki <attila.dusnoki@htecgroup.com>

Add parsing support for value_float, value_floats, value_int, value_ints attributes
Disable failing tests
Resolves Test failures due to IndexError: _Map_base::at migraphx-benchmark/AMDMIGraphX#76

The --py output can be loaded back in the driver. This will embed the migraphx interperter so we can execute the python directly. There is a migraphx_py library which will dynamically load the version of the library for python version is available on the system.

Fixes #1957

Clamping was removed in #1853.

Turns out clamping as necessary to handle overflow/underflow cases. during downcasting, if it overflowed then without clamping it returned infinity.

Python API with documentation updates

Expose get_shape and get_operator methods for instruction_ref object in the python API.

Expose the shape::type_t values to be used by the python api and is required by torch_migraphx to support torchbench models.

* Add driver flag "--exhaustive-tune" to enable tuning, add support for the same in C/C++ and python API

Change download location for onnx model from AWS ONNX to download.onnxruntime.ai

Change to python ONNX package 1.10.0 to handle new ONNX test generation.

Stream sync changes and associated API level changes

Implement operator for CPU and GPU implementations

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

Expose add_literal method in C/C++ api

Add ref and gpu implementations for ONNX op GatherND

Resolves #1032

Implements the ReverseSequence ONNX operator as a parser.

This parser can only handle a constant sequence_lens input. This is the same as what is handled for TensorRT as far as I can tell.
We could handle a variable sequence_lens input; that would require ref and GPU implementations of the operator.
The ONNX backend tests are disabled because this does not handle variable sequence_lens.

Adds following API binding and tests to python :

add_return
add_instruction
add_parameter
create_module.

Follow up to #1128

Add Celu ONNX operator

Add python API to construct shape class

* Implement size ONNX operator and tests