Unable to Get Output Tensors of Custom Model That Has Three Outputs

• Got output tensor for custom model that has three outputs:

  from openvino.runtime import Core
  core = Core()
  model = core.read_model(model="model.xml")
  compiled_model = core.compile_model(model, "CPU")
  infer_request = compiled_model.create_infer_request()
  infer_request.start_async()
  infer_request.wait()
  output = infer_request.get_output_tensor()
  print(output)

• Received error:

  RuntimeError: get_output_tensor() must be called on a function with exactly one parameter.

The ov::InferRequest::get_output_tensor method without arguments can be used for model with only one output.

1. Use ov::InferRequest::get_output_tensor method with argument (index: int) for model that has more than one output.

   output1 = infer_request.get_output_tensor(0)
   output2 = infer_request.get_output_tensor(1)
   output3 = infer_request.get_output_tensor(2)

2. Use the data attribute of the Tensor object to access the output tensor data for the inference results.

   output_buffer1 = output2.data
   output_buffer2 = output2.data
   output_buffer3 = output3.data
   print(output_buffer1)
   print(output_buffer2)
   print(output_buffer3)