GitLab

Add min and max reduction modes
Implement duplicate index handling
Add corresponding reference, onnx, and verify tests.

Introduce dilations attribute to pooling operators reference implementation.

Since ONNX opset version 14, layout attribute has been introduced to LSTM operator which allows two predefined layouts for input and output shapes.  Add corresponding reference, onnx, and verify tests.

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.

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.

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

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.

Implement operator for CPU and GPU implementations

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

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.

Add Celu ONNX operator

* Implement size ONNX operator and tests

Adds EyeLike ONNX parser and unit tests.

Add onnx parser and ref and gpu implementations of ONNX op ScatterND

Implements the IsNaN operator, ref, gpu, and onnx parser.

* Add mean op onnx parser and unit tests
* Refactor parse_mean to use add_broadcastable_binary_op

Add HardSwish to HardSigmoid parser

HardSwish formula is y = x * HardSigmoid<alpha=1/6, beta=0.5>(x)
HardSigmoid parser sets alpha to 1/6 and adds the mul instruction if op name is HardSwish

Resolves #1062

Add onnx parser for operator GreaterOrEqual

Add onnx parser and unit tests for Softsign

* Add onnx parser and unit test

Add HardSigmoid onnx parser and unit tests
Produces mathematical equivalent to ONNX operator through combination of existing pointwise ops.
Resolves #1028

Implementation of the roialign operator. For now, we have only the ref implementation. When we run a model on the GPU, we fall back the execution to use the ref implementation.

Add multinomial op to onnx parser with ref and GPU implementations.

The onnx parser inserts a literal of shape {batch_size, sample_size} with random values in the range [0, 1) and inserts existing ops to compute the cumulative density function. The multinomial operator multiplies the random values by the sum of the CDF and returns the index of the first element of the CDF that is greater than the result, representing samples randomly drawn from [0, class_size) that follow the log-probability distribution.

Resolves #821
Co-authored-by: Shucai Xiao <shucai@gmail.com>

Supports 1,11,13 ONNX Operator Set

Add ability to parse ThresholdedRelu ONNX operator.

Resolves #888
Co-authored-by: Shucai Xiao <shucai@gmail.com>

* add topk operator doe ref, cpu and gpu
* Hash modules for quicker lookup of modules
* add onnx unit test
* add unit tests for the topk operator
Co-authored-by: Paul <pfultz2@yahoo.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* Add pyflakes to CI

* Remove unused imports

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