Select a version

Select a version

No results found. Please clear your search and try again.

EDGE-AI-STUDIO

Edge AI Studio

Select a version
No results found. Please clear your search and try again.
Latest version
Version: 0.9
Release date: 01 Mar 2023
Products
Arm-based processors
AM62A3 1 TOPS vision SoC with RGB-IR ISP for 1-2 cameras, low-power system, video doorbell, security camera AM62A3-Q1 Automotive 1 TOPS vision SoC with RGB-IR ISP for 1-2 cameras, driver monitoring, dashcams AM62A7 2 TOPS vision SoC with RGB-IR ISP for 1-2 cameras, low-power systems, video surveillance, lawn robot AM62A7-Q1 2 TOPS vision SoC with RGB-IR ISP for 1-2 cameras, driver monitoring, front cameras AM68A 8 TOPS vision SoC for 1-8 cameras, machine vision, smart traffic, retail automation AM69A 32 TOPS vision SoC for 1-12 cameras, Autonomous Mobile Robots, Machine Vision, Mobile DVR, AI-BOX TDA4VM Dual Arm® Cortex®-A72 SoC and C7x DSP with deep-learning, vision and multimedia accelerators TDA4VM-Q1 Automotive system-on-a-chip for L2, L3 and near-field analytic systems using deep learning
Hardware development
Evaluation board
J721EXCPXEVM Common processor board for Jacinto™ 7 processors J721EXSOMXEVM TDA4VM and DRA829V socketed system on module (SoM) SK-TDA4VM TDA4VM processor starter kit for edge AI vision systems SK-AM62A-LP AM62A starter kit for low-power Sitara™ processors SK-AM68 AM68 and AM68A starter kit for vision AI and general purpose processors SK-AM69 AM69 and AM69A starter kit for vision AI and general purpose processors

Release Information

Edge AI studio is a collection of tools aimed to accelerate the development of edge AI application on TI embedded devices. 

Model analyzer, formerly known as TI edge AI cloud, is a free online service that allows you to evaluate accelerated deep learning inference on remotely accessed development boards.  With Model analyzer it only takes minutes to login, deploy a model and obtain a variety of performance benchmarks.

Model composer (coming soon) is a tool for training, compiling and deploying models on a local development board.