Machine learning inference for embedded applications reference design


Design files


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 our 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
??image.gallery.download_en_US?? View video with transcript Video

A fully assembled board has been developed for testing and performance validation only, and is not available for sale.

Design files & products

Design files

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

TIDUEB6.PDF (5389 K)

Reference design overview and verified performance test data

SPRR351.ZIP (1613 K)

Detailed schematic diagram for design layout and components

SPRR352.ZIP (30 K)

Complete listing of design components, reference designators, and manufacturers/part numbers

SPRCAG7.ZIP (1464 K)

Design file that contains information on physical board layer of design PCB

SPRR353.ZIP (31509 K)

PCB layer plot file used for generating PCB design layout


Includes TI products in the design and potential alternatives.

Arm-based processors

AM5749Sitara processor: dual Arm Cortex-A15 & dual DSP, multimedia, ECC on DDR, secure boot, deep learning

Data sheet: PDF | HTML

Technical documentation

= Top documentation selected by TI
No results found. Please clear your search and try again.
View all 3
Type Title Date
* Design guide Deep Learning Inference For Embedded Applications Reference Design Sep. 11, 2018
White paper Bringing deep learning to embedded systems (Rev. A) Feb. 26, 2019
More literature Emulation Wiki -- In-depth technical and "how-to" articles, FAQs, etc. Mar. 24, 2011

Related design resources

Software development

PROCESSOR-SDK-AM57X Processor SDK for AM57x Sitara Processors - Linux and TI-RTOS Support

Support & training

TI E2E™ forums with technical support from TI engineers

View all forum topics

Content is provided "as is" by 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, see TI support. ​​​​​​​​