Skip to main content
This section of our documentation is your guide to understanding and improving your machine learning models. Here, you’ll learn how to use Labelbox to run experiments, analyze your model’s performance, and identify high-impact data to improve your model’s accuracy.

What are experiments and model runs?

At the heart of model evaluation in Labelbox are two key concepts: experiments and model runs.
  • Experiment: An Experiment is a container for all your work on a specific model. It’s where you’ll house your data, your model’s predictions, and all the iterations you go through as you develop and refine your model.
  • Model run: A Model Run represents a single iteration or version within an Experiment. Each time you train your model with a new set of hyperparameters, on a different slice of data, or with a new set of labels, you’ll create a new Model Run to track the results.

Model evaluation workflow

The model evaluation workflow in Labelbox is designed to be a continuous cycle of improvement.
  1. Create an experiment: Start by creating an experiment to house your model runs.
  2. Create a model run: Select the experiment and create the model run. You may also create new model runs under existing experiments.
  3. Upload predictions: Upload your model’s predictions to the model run.
  4. Analyze performance: Use Labelbox’s powerful tools to analyze your model’s performance.
  5. Identify opportunities: Discover areas where your model is struggling and identify high-impact data to improve it.
  6. Take action: Send data for re-labeling, find similar data in your catalog, and export data for further analysis.
  7. Iterate: Create a new model run and repeat the process.
By following this workflow, you can systematically improve your model’s performance and build more accurate and reliable machine learning applications.

Getting started

Create your first model run

Explore your model run

Analyze your model runs

Take action on your analysis