Verify and Document the complete ML Workflow

[Sanjana-Siddani]

Description

The inference/ folder contains separate scripts for collecting data, generating labels, preparing the dataset, training the model, and testing it. However, the complete workflow and the correct order for running these scripts are not clearly documented.

This issue will create clear instructions that allow a new contributor to set up and run the existing ML pipeline.

Tasks

• Review all files inside the inference/ folder.
• Document the purpose of each Python script.
• Add the correct execution order for:
• Data collection
• Label generation
• Label validation
• Dataset preparation
• Model training
• Model testing
• Document the input and output files for each step.
• Add commands that can be run from the project root.
• Add troubleshooting notes for common setup errors.
• Verify the instructions in a fresh Python virtual environment.

Acceptance Criteria

• inference/README.md explains the complete workflow.
• Every inference script has a clear purpose.
• Commands can be copied and run from the project root.
• Input and output files are documented.
• Instructions are verified in a fresh virtual environment.
• Another team member reviews the instructions.