[Good First Issue][TF FE]: Support Case operation for TensorFlow models

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.

In order to infer TensorFlow models with Case operation by OpenVINO, TF FE needs to be extended with this operation support.

What needs to be done?

For Case operation support, you need to add the corresponding loader into TF FE op directory and to register it into the dictionary of Loaders. One loader is responsible for conversion (or decomposition) of one type of TensorFlow operation.

Here is an example of loader implementation for TensorFlow Einsum operation:

OutputVector translate_einsum_op(const NodeContext& node) { 
     auto op_type = node.get_op_type(); 
     TENSORFLOW_OP_VALIDATION(node, op_type == "Einsum", "Internal error: incorrect usage of translate_einsum_op."); 
     auto equation = node.get_attribute<std::string>("equation"); 
  
     OutputVector inputs; 
     for (size_t input_ind = 0; input_ind < node.get_input_size(); ++input_ind) { 
         inputs.push_back(node.get_input(input_ind)); 
     } 
  
     auto einsum = make_shared<Einsum>(inputs, equation); 
     set_node_name(node.get_name(), einsum); 
     return {einsum}; 
 } 

In this example, translate_einsum_op converts TF Einsum into OV Einsum. NodeContext object passed into the loader packs all info about inputs and attributes of Einsum operation. The loader retrieves an attribute of the equation by using the NodeContext::get_attribute() method, prepares input vector, creates Einsum operation from OV opset and returns a vector of outputs.

Responsibility of a loader is to parse operation attributes, prepare inputs and express TF operation via OV operations sub-graph. Example for Einsum demonstrates the resulted sub-graph with one operation. In PR https://github.com/openvinotoolkit/openvino/pull/19007 you can see operation decomposition into multiple node sub-graph.

Hint

Case operation is a type of body graph operations that needs special attention to extract and handle body graphs for each case. You can take a look how to approach with body graphs in loaders for While and If operations.

Example Pull Requests

• https://github.com/openvinotoolkit/openvino/pull/19007

Resources

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

Contact points

@openvinotoolkit/openvino-tf-frontend-maintainers

Ticket

TBD