Skip to content

Post-Processing Script

This step is for inputting a post-processing script to ensure that the output from the AI model is correctly interpreted and formatted for analysis and presentation. Note that this step is required for the Bring Your Own Model (BYOM) feature.

Important

If using a model from ADI's Model Zoo, this step will not appear in the build setup process.

To learn how to create custom data processing scripts, see the Data Processing page.

Script editor environment

The script editor operates within a Jupyter-like Python environment, these three imports are mandatory for postprocessing script files:

  • argparse
  • numpy
  • pathlib

These are the only supported libraries in the runtime environment:

  • torch (2.1.2+cpu)
  • torchvision (0.16.2+cpu)
  • tensorflow-cpu (2.15.0)
  • requests (2.32.5)
  • pyyaml (6.0.3)
  • pandas (2.3.3)
  • scipy (1.15.3)
  • matplotlib (3.10.8)
  • opencv-python (4.11.0.86)

It is recommended to develop your script outside EdgeBench. This environment allows users to test custom post-processing logic directly within the platform.

Adding a post-processing script

  1. Use the provided Python template in the editor to interpret and format the model’s output. Modify the logic to suit your use case.

  2. You can click the Copy Script icon to save the script to your dashboard.

    Copy Script

  3. Click Run Test to validate the script against sample data.

    Run Test

  4. If the test compilation finds any errors/warnings, check the Logs pane and resolve the errors or debug the warnings before running the test again.

    Note

    Users can iteratively update and re-run the script until the pre-processing completes successfully.

  5. Once the test compilation passes successfully, click the Download Script icon to save your script.

    Save Script

  6. Click Next to proceed to the next step.

    Note

    The Next button will remain disabled until the test compilation completes successfully and the script is saved.

Logs pane

The Logs Pane, located at the bottom of the interface, displays detailed logs summarizing background activities, errors, and warnings encountered during compilation. This pane can be collapsed or expanded and is a valuable tool for troubleshooting and understanding compilation behavior.