Design Automation


Deep learning APIs for Espressif SoCs

27 October 2021 Design Automation

ESP-DL, recently introduced by Espressif Systems, provides APIs for neural network (NN) inference, image processing, maths operations and deep learning (DL) models. With ESP-DL, developers can use Espressif's SoCs for neural network inference easily and quickly.

Thus far, Espressif’s data show that, in comparison to the company’s ESP32 wireless MCU, when ESP-DL runs on an ESP32-S3 chip the acceleration of a 16-bit detection model is increased by 4,5 times, or 6,25 times in the case of a face recognition model. In addition, the 8-bit face recognition model is 2,5 times faster than the 16-bit model on the ESP32-S3. Furthermore, Espressif offers a tool that can help developers make their own model compatible with the company’s platform.

Since ESP-DL does not need any peripherals, it can be used as a project component. For example, if it is added to the esp-who/components/directory, ESP-DL can be used as a submodule of ESP-WHO, which contains several project-level examples of image-based applications. The accompanying figure below shows what ESP-DL consists of and how it is implemented as a project component.

ESP-DL provides tools that can help developers convert their own model (possibly developed with a third-party platform such as TensorFlow, PyTorch, MXNet, etc.) into an 8-bit or 16-bit model and evaluate the performance of the quantised model.

Model Zoo

ESP-DL also provides certain easy-to-use models such as human face detection, human face recognition, cat face detection, etc., in the so-called Model Zoo. These models can be used out-of-the-box. Other models, such as for colour detection and hand-pose recognition, will be released soon.

Customising a model

In the GitHub tutorial entitled ‘How to Customize a Model Step by Step’ you can find all relevant instructions with a runnable example which will help you implement your model quickly and easily.

Variety of APIs

ESP-DL contains sufficient APIs for developers to build their own model, such as neural networks (NN), image processing and matrix operations. Meanwhile, developers can customise layers and provide feedback if they have any special requirements regarding the API utility.

Software and hardware boost

ESP-DL implements quantised computation and brings about a more efficient kind of software by optimising the assembly and architecture of the C/C++ code. It is worth mentioning that the ESP32-S3, with its vector instructions, high-speed SPI interface and configurable cache memory, achieves a much faster acceleration in AI applications.


Credit(s)



Share this article:
Share via emailShare via LinkedInPrint this page

Further reading:

NVDC power-path control to 1– 6 cell battery systems
iCorp Technologies Power Electronics / Power Management
SG Micro’s SGM41581 is an I2C-controlled narrow voltage direct charging buck boost charge controller designed to simplify robust power delivery in systems that must seamlessly operate from an adapter input or a battery pack.

Read more...
iCorp brings BeeLee’s compact switch and sensor components to local designers
iCorp Technologies Switches, Relays & Keypads
BeeLee’s product catalogue includes (among others) vibration sensors, tilt ball switches, reed switches, hall sensors, optocoupler (photo interrupter) devices, and liquid level switches.

Read more...
Wi-Fi 7 tri-band connectivity module
iCorp Technologies Telecoms, Datacoms, Wireless, IoT
Quectel has introduced the FCE870Q, a compact short range wireless connectivity module designed for next generation IoT devices that require high throughput, low latency, and reliable operation in dense wireless environments.

Read more...
Lower-power Thread and BLE connectivity
iCorp Technologies DSP, Micros & Memory
Espressif has released the ESP32-H21, a low-power wireless SoC aimed at Thread, Matter, Zigbee, and Bluetooth LE device designs.

Read more...
Enabling the next generation of high-performance wireless designs
iCorp Technologies Telecoms, Datacoms, Wireless, IoT
Espressif Systems has expanded its wireless connectivity portfolio with the introduction of the ESP32-E22, a high-performance connectivity co-processor designed for next generation embedded and IoT systems.

Read more...
ST welcomes STM32Cube AI Studio
Design Automation
STMicroelectronics has introduced STM32Cube AI Studio, a new desktop software environment designed to simplify the deployment of artificial intelligence on STM32 microcontrollers.

Read more...
NeoCortec introduces new NeoGW software
Design Automation
This is a powerful multiplatform open-source solution designed to streamline integration between the NeoMesh network and upper-level systems, whether deployed in the cloud or on-premise environments.

Read more...
Keil Studio now in VSCode
Design Automation
Keil Studio, Arm’s latest IDE, now integrates embedded development tools directly into Visual Studio Code providing features like seamless industry tool integration, version control, and a CLI for CI workflows.

Read more...
Tiny power inductor for low noise applications
iCorp Technologies Passive Components
With the evolution of Bluetooth, chips, sensors and other technologies, the design of TWS earphones is becoming smaller and thinner, and the performance and size requirements of integrated inductors need to follow suit.

Read more...
Next-gen Wi Fi 6E connectivity for embedded systems
iCorp Technologies Telecoms, Datacoms, Wireless, IoT
Espressif Systems has expanded its connectivity portfolio with the introduction of the ESP32-E22, the company’s first Wi-Fi 6E connectivity co-processor.

Read more...









While every effort has been made to ensure the accuracy of the information contained herein, the publisher and its agents cannot be held responsible for any errors contained, or any loss incurred as a result. Articles published do not necessarily reflect the views of the publishers. The editor reserves the right to alter or cut copy. Articles submitted are deemed to have been cleared for publication. Advertisements and company contact details are published as provided by the advertiser. Technews Publishing (Pty) Ltd cannot be held responsible for the accuracy or veracity of supplied material.




© Technews Publishing (Pty) Ltd | All Rights Reserved