Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Good First Issue][TF FE]: Support complex tensors for Prod operations #23233

Closed
rkazants opened this issue Mar 4, 2024 · 4 comments · Fixed by #26475
Closed

[Good First Issue][TF FE]: Support complex tensors for Prod operations #23233

rkazants opened this issue Mar 4, 2024 · 4 comments · Fixed by #26475
Assignees
Labels
category: TF FE OpenVINO TensorFlow FrontEnd good first issue Good for newcomers no_stale Do not mark as stale
Milestone

Comments

@rkazants
Copy link
Contributor

rkazants commented Mar 4, 2024

Context

OpenVINO component responsible for support of TensorFlow models is called as TensorFlow Frontend (TF FE). TF FE converts a model represented in TensorFlow opset to a model in OpenVINO opset.
Some audio models use tensors of complex type. Complex type tensor is a tensor that has elements of complex type. For example, 1D tensor with three elements x = [1+2j, 2, -2j].

For supporting Prod operation on complex type tensor, you need to extend the corresponding loader for Prod.

What needs to be done?

The existing loader for Prod needs to be extended by propagating ComplexTypeMark from input to output and to represent output complex type tensor as a floating-point type tensor with auxiliary dimension that concatenates real and imaginary parts of complex tensor.
To validate the extension, the corresponding layer test needs to be updated with complex tensor cases.

Here is an example of how to extend Reshape loader to support complex type tensors:

OutputVector translate_reshape_op(const NodeContext& node) {
    default_op_checks(node, 2, {"Reshape"}, true);
    auto tensor = node.get_input(0);
    auto complex_type_mark = as_type_ptr<ComplexTypeMark>(tensor.get_node_shared_ptr());
    auto shape = node.get_input(1);
    if (complex_type_mark) {
        element::Type complex_part_type = complex_type_mark->get_complex_part_type();
        tensor = complex_type_mark->input_value(0);

        OutputVector concat_inputs;
        concat_inputs.push_back(shape);
        concat_inputs.push_back(make_shared<v0::Constant>(shape.get_element_type(), Shape{1}, 2));

        auto concat = make_shared<v0::Concat>(concat_inputs, 0);
        auto reshape = make_shared<v1::Reshape>(tensor, concat, false);
        set_node_name(node.get_name(), reshape);
        auto complex_reshape = make_shared<ComplexTypeMark>(reshape, complex_part_type);
        return {complex_reshape->output(0)};
    }

    auto reshape = make_shared<v1::Reshape>(tensor, shape, false);
    set_node_name(node.get_name(), reshape);
    return {reshape};
}

Since OpenVINO does not have native support of complex tensors, we handle complex type in intermediate layers by representing them as a floating-point type with additional dimension (specially created) to store real and imaginary parts of the original complex tensor so slicing by the last dimension will give either real or imaginary parts: x[...,0] - real and x[...,1] - imaginary parts.

On the first step, we update default_op_checks with true flag to indicate that loader for Reshape operation now handles complex tensors:

default_op_checks(node, 2, {"Reshape"}, true);

Secondly, we check if complex type mark exists by anticipated inputs. This mark indicates that input tensor of complex type:

auto complex_type_mark = as_type_ptr<ComplexTypeMark>(tensor.get_node_shared_ptr());

Thirdly, we retrieve a floating-point tensor (with additional dimension to store real and imaginary parts) simulating complex tensor:

tensor = complex_type_mark->input_value(0);

After that, we implement conversion for Reshape for this particular case. Since a floating-point tensor simulating complex tensor has additional dimension equal to 2,
we update input target shape by appending 2 value and perform reshape on a floating-point tensor simulating complex tensor.

Finally, since Reshape should produce complex tensor by output we insert a new mark ComplexTypeMark into the output.

To validate support of complex tensors for Reshape, the new layer test TestComplexReshape was added.

Example how to run the layer test:

export TEST_DEVICE=CPU
cd openvino/tests/layer_tests/tensorflow_tests
pytest test_tf_Reshape.py

Example Pull Requests

Resources

Contact points

  • @openvinotoolkit/openvino-tf-frontend-maintainers
  • rkazants in Discord

Ticket

No response

@rkazants rkazants added good first issue Good for newcomers category: TF FE OpenVINO TensorFlow FrontEnd no_stale Do not mark as stale labels Mar 4, 2024
@github-project-automation github-project-automation bot moved this to Contributors Needed in Good first issues Mar 4, 2024
@MonalSD
Copy link
Contributor

MonalSD commented Mar 11, 2024

.take

Copy link
Contributor

Thank you for looking into this issue! Please let us know if you have any questions or require any help.

@mlukasze mlukasze moved this from Contributors Needed to Assigned in Good first issues Mar 11, 2024
@p-wysocki p-wysocki linked a pull request Mar 12, 2024 that will close this issue
@p-wysocki p-wysocki moved this from Assigned to In Review in Good first issues Apr 3, 2024
@mlukasze mlukasze moved this from In Review to Contributors Needed in Good first issues Jun 18, 2024
@hub-bla
Copy link
Contributor

hub-bla commented Sep 7, 2024

.take

Copy link
Contributor

github-actions bot commented Sep 7, 2024

Thank you for looking into this issue! Please let us know if you have any questions or require any help.

@rkazants rkazants linked a pull request Sep 8, 2024 that will close this issue
@mlukasze mlukasze moved this from Contributors Needed to In Review in Good first issues Sep 9, 2024
github-merge-queue bot pushed a commit that referenced this issue Sep 9, 2024
### Details:
- Fixed fifth case of `atan2` implementation (it returned `pi/2` instead
of `-pi/2`).
- Moved `atan2` to `utils`.
- Create helper functions for converting complex number from rectangular
to polar form and the other way around.
- Support complex tensors for `Prod` operations + unit tests.

### Tickets:
 - [None](#23233)


### Resources used:
-
https://math.stackexchange.com/questions/1938894/imaginary-part-of-a-product-of-n-complex-numbers
 - https://en.m.wikipedia.org/wiki/Euler%27s_formula

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
@github-project-automation github-project-automation bot moved this from In Review to Closed in Good first issues Sep 9, 2024
@mlukasze mlukasze added this to the 2024.5 milestone Sep 9, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
category: TF FE OpenVINO TensorFlow FrontEnd good first issue Good for newcomers no_stale Do not mark as stale
Projects
Archived in project
4 participants