Model Repository Guidelines

The submission of the model is done by sharing an open repository containing the models, which will be accessed through the link shared with Skyserve while submission.

Image of directory tree to be maintained for the model repository

All the Models should have the following folder structure:

• /Models Folder

  It contains the models that will be used for inference.

• /SampleData Folder

  Type	Description
  /Input	Contains Input images/files to test the machine learning / deep learning model.
  /Output	Corresponding expected output for the images if the model runs on /Input images.

1. The input file and output file name should follow a specific protocol so that the input image output can be traced back to its corresponding output.

2. [Input Protocol: '{inputfilename}.{extension}'], [Output Protocol: '{inputfilename}-{suffix}.{extension}']

3. Please refer to the Appendix for more details.

• /Utils Folder

  Any additional logic required to infer the model apart from the code written in main.py should be kept inside the Utils folder. This can contain Helper classes and other utility functions.

• /Runtime Folder

  The code should be written such that the outputs are written in the '/Runtime' directory. Before the submission of the repository, the files written in this directory should be moved to the '/SampleData/Output' directory for given inputs in the '/SampleData/Input' directory. The '/Runtime' directory will then be used to write outputs that would be written after a test run during the submission of model.

• /Intermediate Folder

  This directory shall be used to write any intermediate outputs from the pre-processing of the model.

• /main.py

  The main Python script (inference script), which will have the code to infer the Model present in the /Models folder. The pre-processing, post-processing steps can be invoked from this script itself with their code either residing in '/main.py' or in any helper function present in a separate file in the '/Utils' Folder

• /README.md

  General readme file regarding the Model Input/Model Output and other required information

• /requirements.txt

  List of python library requirements, we recommend generating this in a specific python virtual environment so that the global modules/library of python doesn’t affect the version or list of libraries required in case it is being generated via some third party tool like `pipreqs.

• /system_specs.txt

  Any hardware/GPU-related info/points requirements can be mentioned in this text file.