Using DOPE at Different Image Resolutions
===============================================

Overview
------------

The DOPE network architecture, as outlined in the `original
paper <https://arxiv.org/abs/1809.10790>`__, can receive input images of
arbitrary size and subsequently produce output belief maps of the
corresponding dimensions.

However, the ONNX format used to run this network on Triton or TensorRT
is not as flexible, and an ONNX-exported model **does NOT** support
arbitrary image sizes at inference time. Instead, the desired input
image dimensions must be explicitly specified when preparing the ONNX
file using the ``dope_converter.py`` script, as referenced in the
:doc:`quickstart </repositories_and_packages/isaac_ros_pose_estimation/isaac_ros_dope/index>`.

Tutorial Walkthrough
--------------------

#. Complete until ``Run Launch File`` of the quickstart :doc:`here </repositories_and_packages/isaac_ros_pose_estimation/isaac_ros_dope/index>`.

#. Under the ``Run Launch File`` section, run the ``dope_converter.py`` script with the two
   additional arguments ``row`` and ``col`` specifying the desired input
   image size:

   .. code:: bash

      ros2 run isaac_ros_dope dope_converter.py --format onnx \
         --input ${ISAAC_ROS_WS}/isaac_ros_assets/models/dope/Ketchup.pth --output ${ISAAC_ROS_WS}/isaac_ros_assets/models/dope/Ketchup.onnx \
         --row 1080 --col 1920

#. Continuing in the quickstart's ``Run Launch File`` section, complete the data source-specific setup.
   Then, launch the data source-specific ``isaac_ros_examples.launch.py`` file with two additional arguments
   ``network_image_height`` and ``network_image_width`` specifying the
   desired input image size.

   For example:

   .. code-block:: bash
      :class: no-copybutton

      ros2 launch isaac_ros_examples isaac_ros_examples.launch.py <data source-specific arguments> ... \
         network_image_height:=1080 network_image_width:=1920  # Add these arguments to the launch command

#. Continue with the rest of the quickstart. You should now be able to
   detect poses in images of your desired size.