DEEPCRAFT™ Studio

Infineon's platform for developing Edge AI models

nobutton

Overview

DEEPCRAFT™ Studio is a development platform for AI models targeted for use on edge devices. Use DEEPCRAFT™ Studio's unique and powerful modeling capabilities to make custom classification, regression or computer vision Edge AI models. Bring your own data, or use one of our many DEEPCRAFT™ Studio Accelerators with the datasets, preprocessing, model architecture and instructions needed to make your machine learning model development even easier.

Key Features

  • End-to-end AI model development
  • Fast time to market
  • Build custom models for any MCU
  • Create production-ready AI models
  • For both ML experts and non-experts
  • Unique graph-based UX
  • Use any time-series or vision data
  • Studio Accelerators for fast development
  • Deep Learning based
  • Optimized output for MCUs and NPUs

About

DEEPCRAFT™ Studio - development platform for Edge AI models

DEEPCRAFT™ Studio (formerly Imagimob Studio) is a platform for developing AI models for edge devices. The platform is designed to support users in creating robust, high-quality models that are ready for deployment in commercial products.

Use DEEPCRAFT™ Studio's powerful modeling capabilities to make custom Edge AI models. Developers can stream data into the platform, or import their own data to get started. For faster development, use one of our DEEPCRAFT™ Studio Accelerators as a starting point. These open-source models include the datasets, preprocessing, model architecture and instructions that developers can utilize as basis to train production-ready Edge AI models. The platform enables model development based on time series and image data.

DEEPCRAFT™ Studio uses an intuitive Graph UX interface. This lets users visualize the end-to-end machine learning workflow as graphs, providing a clear understanding of the modeling workflow from building to evaluating machine learning models.

Together with ModusToolbox™ and AURIX™ Development Studio, DEEPCRAFT™ Studio offers customers an end-to-end solution for machine learning model development and deployment into products.

Download DEEPCRAFT™ Studio

DEEPCRAFT™ Studio enables countless Edge AI use cases

DEEPCRAFT™ Studio enables developers to train models for a wide range of use cases. With computer vision or time series data, the platform makes it easier to create Edge AI models using data from various sensors. These models can be used for smart homes and buildings, health and lifestyle, automotive, and industrial use cases, to name a few.

Below are just some of the nearly endless use cases for various sensors.

For cameras, using vision-based models:

Object detection

Presence detection

Image classification

For radar-based models:

Gesture detection

Presence detection

Surface and material detection

For microphones, using audio-based models:

Audio classification of different sounds

Direction of arrival of various sounds

Voice control and keyword detection

Predictive maintenance

For IMUs/accelerometers:

Fall detection

Human motion detection

Integrations make deploying models made in DEEPCRAFT™ Studio easy.

You can use DEEPCRAFT™ Studio to make Edge AI models for any MCU. To make deployment as easy to use as possible, we have some key integrations for Infineon hardware. For PSOC™ and TRAVEO™ MCUs, we have an integration with ModusToolbox™. For AURIX™ MCUs, we have an integration with AURIX™ Development Studio.
Learn more about these integrations

DEEPCRAFT™ Studio - development platform for Edge AI models

DEEPCRAFT™ Studio (formerly Imagimob Studio) is a platform for developing AI models for edge devices. The platform is designed to support users in creating robust, high-quality models that are ready for deployment in commercial products.

Use DEEPCRAFT™ Studio's powerful modeling capabilities to make custom Edge AI models. Developers can stream data into the platform, or import their own data to get started. For faster development, use one of our DEEPCRAFT™ Studio Accelerators as a starting point. These open-source models include the datasets, preprocessing, model architecture and instructions that developers can utilize as basis to train production-ready Edge AI models. The platform enables model development based on time series and image data.

DEEPCRAFT™ Studio uses an intuitive Graph UX interface. This lets users visualize the end-to-end machine learning workflow as graphs, providing a clear understanding of the modeling workflow from building to evaluating machine learning models.

Together with ModusToolbox™ and AURIX™ Development Studio, DEEPCRAFT™ Studio offers customers an end-to-end solution for machine learning model development and deployment into products.

Download DEEPCRAFT™ Studio

DEEPCRAFT™ Studio enables countless Edge AI use cases

DEEPCRAFT™ Studio enables developers to train models for a wide range of use cases. With computer vision or time series data, the platform makes it easier to create Edge AI models using data from various sensors. These models can be used for smart homes and buildings, health and lifestyle, automotive, and industrial use cases, to name a few.

Below are just some of the nearly endless use cases for various sensors.

For cameras, using vision-based models:

Object detection

Presence detection

Image classification

For radar-based models:

Gesture detection

Presence detection

Surface and material detection

For microphones, using audio-based models:

Audio classification of different sounds

Direction of arrival of various sounds

Voice control and keyword detection

Predictive maintenance

For IMUs/accelerometers:

Fall detection

Human motion detection

Integrations make deploying models made in DEEPCRAFT™ Studio easy.

You can use DEEPCRAFT™ Studio to make Edge AI models for any MCU. To make deployment as easy to use as possible, we have some key integrations for Infineon hardware. For PSOC™ and TRAVEO™ MCUs, we have an integration with ModusToolbox™. For AURIX™ MCUs, we have an integration with AURIX™ Development Studio.
Learn more about these integrations

Documents

Documents

Design resources