Check out ESP-DL!

ESP-DL provides APIs for Neural Network (NN) Inference, Image Processing, Math Operations and Deep Learning Models. With ESP-DL, developers can use Espressif’s SoCs for neural network inference easily and quickly. Thus far, our data show that, in comparison to ESP32, when ESP-DL runs on ESP32-S3 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 ESP32-S3. Furthermore, we offer a tool that can help developers make their own model compatible with our 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 figure below shows what ESP-DL consists of, and how ESP-DL is implemented as a project component.

Platform Conversion

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 quantized 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. You can now use these models out-of-the-box. Other models, such as those regarding color detection and hand-pose recognition, will be released soon.

Customizing a Model

In our 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.

https://github.com/espressif/esp-dl/tree/master/tutorial

Variety of APIs

ESP-DL contains sufficient APIs for developers to build their own model, such as Neural Network (NN), Image Processing, Matrix Operations. Meanwhile, developers can customize layers and provide us with their feedback if they have any special requirements about the API utility.

Software and Hardware Boost

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

More details about ESP-DL can be found on our relevant GitHub page https://github.com/espressif/esp-dl.

Pricing and Availability

Pricing and availability info please visit email: sales.europe@macnica.com.

About Espressif Systems

Espressif Systems (Shanghai) Pte. Ltd. is a fabless semiconductor company, with headquarters in Shanghai Zhangjiang High-Tech Park, providing low power Wi-Fi and Bluetooth SoCs and wireless solutions for the Internet of Things (IoT). The company build the widely popular ESP8266 and ESP32 chips with an innovative team of chip-design specialists, software and firmware developers and marketers. Espressif is committed to providing the best IoT devices and software platforms in industry.

The company also helps their customers build their own solutions and connect with other partners in the IoT ecosystem. Their passion lies in creating state-of-the-art chipsets and enabling partners to deliver great products. Espressif’s products are widely deployed in the tablet, OTT boxes, cameras, and Internet of Things markets.

For more information, please visit https://www.espressif.com.

Über die Macnica ATD Europe GmbH

Macnica’s European headquarter was originally established in the UK in 2006, and moved to Germany in July 2008, to increase efficacy of its service for European cus-tomers.
By it’s acquisition of the Munich based company Scantec Mikroelektronik in 2014 Macnica Europe formed a powerful semiconductor distribution with headquarters in Munich and Ingolstadt and numerous sales offices in Europe offering an attractive and competitive portfolio of highly sophisticated devices.
Macnica provides end to end support from design-in to production through its global service network to its customers, regardless of the final destination of the product shipment to customers‘ manufacturing locations.

About Macnica, Inc.
Macnica was established in 1972 as a semiconductor distribution company headquar-tered in Yokohama, Japan, and has over 84 sales offices worldwide in eastern Asia, Europe and the USA. Total number of employees is over 3,000 and its consolidated revenue for fiscal 2019 was approximately US$ 5 B.
Macnica is famous for having an excellent engineering team of more than 900 appli-cation support engineers, IC designers and software developers with strong focus on providing technical support for its customers including custom design services. Mac-nica is continuing to extend its presence globally by having successful partners in strategic areas in the electronics market.

Firmenkontakt und Herausgeber der Meldung:

Macnica ATD Europe GmbH
Nürnberger Str. 34
85055 Ingolstadt
Telefon: +49 (841) 88198-0
Telefax: +49 (841) 88198199
http://www.macnica.eu/de

Ansprechpartner:
Josef Sigl
Marketing
Telefon: +49 (89) 899143-15
Fax: +49 (89) 899143-17
E-Mail: josef.sigl@macnica.com
Für die oben stehende Pressemitteilung ist allein der jeweils angegebene Herausgeber (siehe Firmenkontakt oben) verantwortlich. Dieser ist in der Regel auch Urheber des Pressetextes, sowie der angehängten Bild-, Ton-, Video-, Medien- und Informationsmaterialien. Die United News Network GmbH übernimmt keine Haftung für die Korrektheit oder Vollständigkeit der dargestellten Meldung. Auch bei Übertragungsfehlern oder anderen Störungen haftet sie nur im Fall von Vorsatz oder grober Fahrlässigkeit. Die Nutzung von hier archivierten Informationen zur Eigeninformation und redaktionellen Weiterverarbeitung ist in der Regel kostenfrei. Bitte klären Sie vor einer Weiterverwendung urheberrechtliche Fragen mit dem angegebenen Herausgeber. Eine systematische Speicherung dieser Daten sowie die Verwendung auch von Teilen dieses Datenbankwerks sind nur mit schriftlicher Genehmigung durch die United News Network GmbH gestattet.

counterpixel