Machine Learning Backends

This documentation describes Heartex platform version 1.0.0, which is no longer supported. For information about the machine learning SDK in Label Studio Enterprise Edition, the equivalent of Heartex platform version 2.0.x, see Write your own ML backend.

You can easily connect your favorite machine learning framework with Heartex Machine Learning (ML) SDK or Label Studio ML toolkit. That gives you the opportunities to use:

• Pre-labeling: Use model predictions for pre-labeling (e.g. make use on-the-fly model predictions for creating rough image segmentations for further manual refinements)
• Autolabeling: Create automatic annotations
• Online Learning: Simultaneously update (retrain) your model while new annotations are coming
• Active Learning: Perform labeling in active learning mode - select only most complex examples
• Prediction Service: Instantly create running production-ready prediction service

Connecting ML backend

Connecting Machine Learning backend could be done in 2 steps:

1. Create and launch Heartex/Label Studio-compatible Machine Learning (ML) server according to
   • Tutorials,
   • Quickstart guide,
   • or Label Studio documentation.
2. Go to Project Settings page, then switch to the Machine Learning tab and click on Add Custom Model. You will be prompted to enter ML backend title and URL.

Tutorials

• Create the simplest ML backend
• Text classification with Scikit-Learn
• Transfer learning for images with PyTorch

Quickstart

Here is a quick example tutorial on how to run the ML backend with a simple text classifier using Label Studio ML toolkit:

0. Clone repo

   git clone https://github.com/heartexlabs/label-studio

1. Setup environment

   cd label-studio
   pip install -e .
   cd label_studio_enterprise/ml/examples
   pip install -r requirements.txt

2. Create new ML backend

   label-studio-ml init my_ml_backend --script label_studio_enterprise/ml/examples/simple_text_classifier.py

3. Start ML backend server

   label-studio-ml start my_ml_backend