[Good First Issue]: Support aten::reflection_pad1d, aten::reflection_pad3d for pytorch models

[mvafin]

Context

OpenVINO component responsible for support of PyTorch models is called as PyTorch Frontend (PT FE). PT FE converts a model represented as TorchScript model to a model in OpenVINO opset.
aten::reflection_pad2d is already supported, what needs to be done is to also support other sizes.

What needs to be done?

• Implement conversion rule and/or transformation to support the new operation.
• Implement operation tests in tests/layer_tests/pytorch_tests. Please consider different data types, but keep reasonable number of test cases

Example Pull Requests

#18998

Resources

• torch.nn.ReflectionPad1d description
• Contribution guide - start here!
• What is OpenVINO?
• OpenVINO PyTorch Frontend
• Blog post on contributing to OpenVINO
• User documentation

Contact points

@openvinotoolkit/openvino-pytorch-frontend-maintainers

Ticket

TBD

[thinhngo-x]

.take

[github-actions]

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

[thinhngo-x]

Hello @mvafin, can you please show me where the aten::reflection_pad2dhas been implemented? Thanks.

[mvafin]

@thinhngo-x It is supported here:

openvino/src/frontends/pytorch/src/transforms/prim_list_construct_pad.cpp

Line 87 in a78d914

} else if ((pad_op = cast_fw_node(m.get_match_root(), "aten::reflection_pad2d"))) {

[p-wysocki]

Hello @thinhngo-x, are you still working on this?

[duydl]

.take

[github-actions]

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

[duydl]

Hi, I have some question.

• How pytorch/src/transforms/prim_list_construct_pad.cpp is related to pytorch/src/op/pad.cpp.

• The test for ReflectionPad in test_pad.py passes (also torch.nn.ReflectionPad1d is the same as ReflectionPad2d and ReflectionPad3d i.e accepts 4-tuple and returns same output).

  openvino/tests/layer_tests/pytorch_tests/test_pad.py

  Line 205 in 68bdbbe

  class TestReflectionPad(PytorchLayerTest):

  
  So it seems to me the relevant logic is already converted to openVINO ops.

Thank you.

[jagadeeshmadinni]

.take

[github-actions]

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