[Good First Issue]: Support aten::fft_fftn

[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.

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
• Enable the model in model_hub_tests:

  openvino/tests/model_hub_tests/torch_tests/hf_transformers_models

  Line 102 in 6a50ea3

  google/fnet-base,fnet,xfail,Unsupported op aten::fft_fftn aten::real

Example Pull Requests

#17999

Resources

• Contribution guide - start here!
• What is OpenVINO?
• OpenVINO PyTorch Frontend
• How to build OpenVINO
• Blog post on contributing to OpenVINO
• User documentation

This will enable the google/fnet-base model from Hugging Face. You can use the following script to reproduce the issue:

from transformers import AutoTokenizer, AutoModel
from openvino import convert_model

tokenizer = AutoTokenizer.from_pretrained("google/fnet-base")
model = AutoModel.from_pretrained("google/fnet-base", torchscript=True)
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt', padding='max_length', truncation=True, max_length=512)
inputs = dict(encoded_input)

m = convert_model(model, example_input=inputs)

Contact points

@openvinotoolkit/openvino-pytorch-frontend-maintainers

Ticket

TBD

[siddhant-0707]

.take
PR #21705

[github-actions]

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

[github-actions]

Thanks for being interested in this issue. It looks like this ticket is already assigned to a contributor. Please communicate with the assigned contributor to confirm the status of the issue.

[p-wysocki]

I am happy to announce that we have created a channel dedicated to Good First Issues support on our Intel DevHub Discord server! Join it to receive support, engage in discussions, ask questions and talk to OpenVINO developers.

[mvafin]

@siddhant-0707 Hi, do you have plans to finish PR, it will be removed soon, due to inactivity?

[mlukasze]

awaiting response from contributor.
further actions based on his decision.

[hibahkhan2022]

.take

[github-actions]

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

[mvafin]

@hibahkhan2022 Please pay attention that after the #28482 the implementation will be different. It can be implemented as an operation conversion, not as transformation.