Here at Modzy, we created an end-to-end integration that uses Sagemaker to train a ML model and then automates the deployment process to the Modzy platform, thus creating an automated model deployment pipeline.

To increase the probability of models making it to the production system and deliver value, Modzy can integrate with the most popular model training tools and frameworks. These integrations allow data scientists to continue using their preferred training platform and tailor their existing pipelines in a way such that the end product is a Modzy-compatible containerized model.

Integration Components

Modzy integrations with training platforms like Sagemaker typically follow this general process flow:

  • Train a model with any combination of tools, frameworks, or languages.
  • Send the trained model to their Modzy account.
  • Convert model to a Modzy compatible Docker container.
  • Deploy the model image and static metadata for the model to Modzy’s platform for use in production.

With Modzy, users have automatic containerization and deployment support for Sagemaker into Modzy’s Python SDK. To begin using this capability, you need (1) the raw output of a trained Sagemaker or MLFlow model, and (2) the model artifacts saved in an AWS s3 bucket or Azure Blob.

Once you have met these requirements, use Modzy’s Python SDK in your preferred editor (my tip: Jupyter Notebooks work great) and follow a few steps to deploy your model to Modzy:

  • Complete a yaml file with documentation about your model and provide any additional metadata files for the specific model type that you chose. In the case of image classification, you will need to provide a labels.json file that contains a mapping between numerical classes and human readable labels.
  • Include credentials required to access your cloud storage blob that contains your model artifacts, specify the path to your weights file(s) and additional model resources, define your model type (e.g., Image Classification), and pass this information to Modzy’s Model Converter through the SDK.
  • Execute the converter and see your model deployed to your environment in just minutes.

For data scientists and developers who wish to add a more programmatic approach to their MLOps pipeline, Modzy’s SDK deployment capability unlocks the potential for automation, improved efficiency, and most importantly, a significant improvement in speed to production.

Integration in Action

Did this page help you?