How to run a VGF file with ML SDK Scenario Runner and ML Emulation Layer for Vulkan®
====================================================================================

1. Use the VGF Dump Tool to generate a Scenario Template. To run a scenario on the ML SDK Scenario Runner,
you must have a scenario specification in the form of a JSON file:

.. code-block:: bash

    $vgf_dump --input ${NAME}.vgf --output scenario.json --scenario-template

.. note::
   For more information about VGF Library and the VGF Dump Tool, see: :ref:`ML SDK VGF Library`


2. The generated :code:`scenario.json` file contains placeholder names for input and output bindings
   for the scenario. You must replace these names with the actual input and output filenames that will
   be used when running the scenario. In the example :code:`scenario.json` file generated in the preceding step:

   a. Replace the name TEMPLATE_PATH_TENSOR_INPUT_0 with the actual input file :code:`input-0.npy`.

   b. Replace the name TEMPLATE_PATH_TENSOR_OUTPUT_0 with the actual output filename :code:`output-0.npy`.

.. note::
    For more information about the test description format, see:
    :ref:`JSON Test Description Specification`.


3. Run the ML SDK Scenario Runner on the ML Emulation Layer for Vulkan®:

.. code-block:: bash

    scenario-runner --scenario scenario.json

The output from the scenario is produced as a file named :code:`output-0.npy`. The file is specified in scenario.json.

.. note::
   For more information about building and running the ML SDK Scenario Runner, see: :ref:`ML SDK Scenario Runner`.

   For more information about building and setting up the Emulation Layer, see:
   :ref:`ML Emulation Layer for Vulkan®`