Cookie
This website requires cookies to provide all of its features. For more information on what data is contained in the cookies, please see our Privacy Policy page. To accept cookies from this site, please click the Accept button below.
| 供应商 | Synopsys |
|---|---|
| 型号 | 3520 MAC DNN Option for EV Vision Processor IP |
| 类型 | Soft IP |
| 到期日 | Available on request |
| 源网址 | View more |
| 特征 | DNN accelerator delivers up to 35 TOPS performance DNN accelerator features advanced hardware and software techniques for improving performance and reducing bandwidth and latency High productivity MetaWare EV Development Toolkit™s DNN mapping tool automatically dispatches processing tasks to available hardware resources for faster execution |
| 详情页 | View more |
| 附件名称 | ev7x-ds.pdf |
| 附件链接 | View more |
The DesignWare ARC EV7x Embedded Vision Processors offer an optional deep neural network (DNN) accelerator for fast and accurate detection of a wide range of objects such as faces, pedestrians, and hand gestures. In addition to supporting convolutional neural networks (CNNs), the DNN supports batched LSTMs (long short-term memories) for applications that require time-based results, such as predicting the location of a pedestrian based on their observed path and speed. The EV7x DNN supports any CNN, including popular networks such as AlexNet, GoogLeNet, Yolo, Faster R-CNN, SqueezeNet, and ResNet.
The optional embedded DNN accelerator adds scalable deep learning and AI capabilities to the EV7x family. The DNN accelerator is optimized for CNNs and batched or convolutional Recurrent Neural Networks (RNNs) or batched LSTMs and includes advanced hardware features to support the latest pruning, compression and layer merging techniques to increase performance and minimize bandwidth. The DNN can be configured from 880 multiply-accumulators (MACs) up to 14,080 MAC versions. Most of the MACs are used for 2D convolutions while a portion is dedicated to 1D convolutions needed for fully connected layers. The DNN datapath supports 8- and 12-bit data precision.
The DNN accelerator supports flexible activation functions, including ReLU, PReLU, ReLU6, tanh and sigmoid. The EV7x supports all CNNs including popular networks such as MobileNet, GoogLeNet, ResNet, Yolo, Faster R-DNN, and ICNet. Designers can run CNN graphs originally trained for 32-bit floating point hardware on the EV7x?s DNN accelerator using 8- or 12-bit resolution significantly reducing the power and area of their designs while maintaining high levels of detection accuracy.
In addition to supporting CNNs, the DNN supports batched LSTMs (long short-term memories) for applications that require time-based results, such as predicting the location of a pedestrian based on their observed path and speed.
The DNN accelerator is supported by a high-performance DMA for transferring image data from external memory into the internal closely coupled memories.
FAQ - Frequently Asked Questions
Welcome to Sparsh\'s FAQ! Here you\'ll find answers to our most asked questions. Still have something we should know? Send us an email, we\'re happy to help!
Q1: How can I change my shipping address?
A1: Consectetur morbi, suscipit donec semper vitae sed a class vivamus. Sodales montes porttitor adipiscing nisl sit dui sem fringilla elit. Sagittis lacinia montes nisl mollis lobortis cras nisi. Conubia montes odio taciti magnis morbi mauris lorem pulvinar mollis aliquam. Faucibus facilisi tempus tincidunt eu laoreet. Porta donec vitae suscipit habitasse fermentum vivamus!
- Eget est ad potenti primis id rhoncus vestibulum vestibulum. Ante est vel mattis mattis. Vel eleifend auctor lorem, odio proin quisque potenti parturient euismod. Tristique massa quis morbi netus magna pretium laoreet. Inceptos eget massa ac lacinia vitae suspendisse orci nascetur vel torquent. Feugiat eleifend eget aenean facilisi sapien proin leo dictumst semper orci ipsum? Ultrices duis tellus consequat nostra.
Q2: How do I activate my account?
A2: The instructions to activate your account will be sent to your email once you have submitted the registration form. If you did not receive this email, your email service provider’s mailing software may be blocking it. You can try checking your junk / spam folder or contact us at magento@sparsh-technologies.com
Q3: How do I cancel my orders before I make a payment?
A3: After logging into your account, go to your Shopping Cart. Here, you will be able to make a payment or cancel your order. We will not give refunds if payment is verified.
Q4: How long will it take for my order to arrive after I make payment?
A4: Members who ship their orders within Inida should expect to receive their orders within 2 working days upon payment verification depending on the count of orders received.
If you experience delays in receiving your order, contact us immediately and we will help to confirm the status of your order.
Q5: What are the payment methods available?
A5: At the moment, we only accept Credit/Debit cards and Paypal payments.
Q6: How do I make payments using Paypal? How does it work?
A6: Paypal is the easiest way to make payments online. While checking out your order, you will be redirected to the Paypal website. Be sure to fill in correct details for fast & hassle-free payment processing. After a successful Paypal payment, a payment advice will be automatically generated to Samplestore.com system for your order.
It\'s fast, easy & secure.