威強電推出應用於圖像處理的計算加速卡-Mustang-M2AE-MX1

Nov 27, 2019

IEI Event News
Mustang_M2AE_MX1_Accelerator_Deep_Learning
特色 介紹 外型尺寸
規格 訂購資訊
 
特色

M.2 AE key form factor (22 x 30 mm)

1 x Intel® Movidius™ Myriad™ X VPU MA2485

Power efficiency, approximate 5W

Operating Temperature -20°C to 60°C

Powered by Intel's OpenVINO™ toolkit

M2AE-prod-pic

介紹

Mustang-M2AE-MX1M.2 AE-KEY 加速卡包含一個Intel® Movidius™ Myriad™ X VPU,為緊湊型和一般嵌入式系統,提供靈活的AI推論解決方案。

VPU是視覺處理單位的縮寫。它使AI運行更加快速,且適合低功耗的應用,像是監視器、零售業、交通運輸。利用省電和高效能的優勢,在DNN拓樸作業上,對AI邊緣運算裝置而言相當完美地減少總電量的消耗,並且對可充電的邊緣運算設備來說,能有更長的運作時間。

Intel® Movidius™ Myriad™ X VPU的重要特色:

Native FP16 support

Rapidly port and deploy neural networks in Caffe and Tensorflow formats

End-to-End acceleration for many common deep neural networks

Industry-leading Inferences/S/Watt performance


外型尺寸
Mustang_AI_Depp_Learning_Dimensions

規格
Model Name Mustang-M2AE-MX1
Main Chip 1 x Intel® Movidius™ Myriad™ X MA2485 VPU
Operating Systems Ubuntu 16.04.3 LTS 64bit, CentOS 7.4 64bit, Windows® 10 64bit
Dataplane Interface M.2 AE Key
Power Consumption Approximate 5W
Operating Temperature -20° C to 60°C
Cooling Active Heatsink
Dimensions 22 x 30 mm
Operating Humidity 5% ~ 90%
Support Topology AlexNet, GoogleNetV1/V2, MobileNet SSD, MobileNetV1/V2, MTCNN, Squeezenet1.0/1.1, Tiny Yolo V1 & V2, Yolo V2, ResNet-18/50/101
*For more topologies support information please refer to Intel® OpenVINO™ Toolkit official website.


訂購資訊
Part No. Description
Mustang-M2AE-MX1-R10 Computing Accelerator Card with 1 x Intel® Movidius™ Myriad™ X MA2485 VPU,M.2 AE key interface, 2230, RoHS