Machine learning inference for embedded applications reference design
This product has been released to the market and is available for purchase. For some products, newer alternatives may be available.

Description & Features

Technical documentation

Support & Training

Order Now

See the Important Notice and Disclaimer covering reference designs and other TI resources.

Key Document


This reference design demonstrates how to use TI Deep Learning (TIDL)/Machine Learning on a Sitara AM57x System-on-Chip (SoC) to bring deep learning inference to an embedded application. This design shows how to run deep learning inference on either C66x DSP cores (available in all AM57x SoCs) and Embedded Vision Engine (EVE) subsystems, which are treated as black boxed deep learning accelerators on the AM5749 SoC.

This reference design is applicable to any application that is looking to bring deep learning/machine learning inference into an embedded application. Customers looking to quickly get started with a deep learning network or to evaluate their own networks performance on an AM57x device will find a step-by-step guide on how to use TIDL available as part of TI’s free AM57x Processor SDK.

  • Embedded deep learning inference on AM57x SoC
  • Performance scalable TI deep learning library (TIDL library) on AM57x using C66x cores only, EVE subsystems only, or C66x + EVE combination
  • Performance optimized reference CNN models for object classification, detection and pixel-level semantic segmentation
  • Full walk-through of TIDL development flow: training, import and deployment
  • Benchmarks of several popular deep learning networks on AM5749
  • This reference design is tested on AM5749 IDK EVM and includes TIDL library on C66x core and EVE subsystem, reference CNN models and getting started guide

See the Important Notice and Disclaimer covering reference designs and other TI resources.


Schematic/Block Diagram

Quickly understand overall system functionality.

Download Schematic

Design Guide

Get results faster with test and simulation data that's been verified.

Download Design Guide

Design Files

Download ready-to-use system files to speed your design process. Get Viewer.

Download Design Files

TI Devices (1)

Order samples, get tools and find more information on the TI products in this reference design.

Part Number Name Product Family Sample & Buy Design Kits & Evaluation Modules
AM5749  Sitara processor: dual Arm Cortex-A15 & dual DSP, multimedia, ECC on DDR, secure boot, deep learning  Processors  Sample & Buy View Design Kits & Evaluation Modules

CAD/CAE symbols

Part # Package | Pins CAD File (.bxl) STEP Model (.stp)
AM5749 Download

Texas Instruments and Accelerated Designs, Inc. have collaborated together to provide TI customers with schematic symbols and PCB layout footprints for TI products.

Step 1: Download and install the free download.

Step 2: Download the Symbol and Footprint from the CAD.bxl file table.

Technical documentation

See the Important Notice and Disclaimer covering reference designs and other TI resources.

Data sheet (1)
Title Type Size (KB) Date
PDF 5226 15 Dec 2019
User guide (2)
Title Type Size (KB) Date
PDF 1697 11 Sep 2019
PDF 5389 11 Sep 2018
White paper (1)
Title Type Size (KB) Date
PDF 1349 26 Feb 2019
Design files (4)
Title Type Size (KB) Date
ZIP 31509 16 Jul 2018
ZIP 30 25 Jun 2018
ZIP 1464 25 Jun 2018
ZIP 1613 25 Jun 2018
Related Tools & Software

Software development (1)

Name Part Number Software Type
Processor SDK for AM57x Sitara Processors - Linux, TI-RTOS and Android Support  PROCESSOR-SDK-AM57X  Software development kit (SDK) 

Support & training

TI E2E™ forums with technical support from TI engineers

Search our extensive online knowledge base where millions of technical questions and answers are available 24/7.

Search answers from TI experts

Content is provided 'AS IS' by the respective TI and Community contributors and does not constitute TI specifications.
See terms of use.

If you have questions about quality, packaging, or ordering TI products visit our Support page.

Technical articles