Skip to the content

Run any ML framework

There are many great ML frameworks and solutions in the market and our strategy is to let you choose. The Node is designed to host different 3rd party frameworks and we currently support all Python based frameworks, such as:

  • TensorFlow
  • Scikit-learn
  • Keras
  • PyTorch

Read More about Machine Learning at the Edge

Bring, Manage and Deploy your own ML models

With Crosser Edge ML Ops functionality.

All you need for the life-cycle of your ML models. A central Resource catalog in Crosser Cloud is used to manage all your ML resources. You can upload trained ML models as well as Python scripts and then easily reference them when building flows. When you deploy these flows onto edge nodes the system will make sure that all resources needed are downloaded into the relevant edge nodes.

When a flow is updated, e.g. by referencing a new ML model, all edge nodes are automatically updated with a single operation. Flow versioning is used to keep track of your changes.

You bring the ML Model

Crosser brings the rest. A unique mix of Drag-and-drop and custom innovation.

Everything you need for collecting, cleaning, preparing and structuring the data before your ML model and all the logic and connectors you need after your model is provided by Crosser. The Flow Studio enables you to build flows and data pipelines faster than ever with drag-and-drop and a rich library of pre-built modules.

We let you focus on the skills that makes you unique, we take care of the rest.

USE CASE

Vision Inspection for Industrial IoT

Using video cameras as sensors in industrial IoT applications is becoming more and more popular. The reason is of course that it opens up for many interesting applications, such as:

  • Vision Inspection for Yield optimization - Identify scrap material and/or products as early as possible in the process
  • Count and measure - Count products, objects, people and measure position, alignment, color and other attributes
  • Intrusion detection - Trigger an alarm or stop a machine when people or objects get too close or enter where they shouldn’t be.

Crosser Edge Analytics allows you to use off-the-shelf cameras and faster and easier than ever build Vision Inspection solutions.

Learn more about the use case here

Try Crosser For Free

Start innovating today. How it works:

  1. Get an account
  2. Log in and start designing your flows in the sandbox
  3. Download the Crosser Container to your local test node
  4. Test with real data