Neural Network Module (NNM)

Neural Network Module (NNM) a USB module that designed for Deep Learning inference on various edge application. NNM is powered by high performance, low power Sophon BM1880 chip.

nnm top image for mobile

Specifications

Processor Sophon BM1880
Supported AI Framework Caffe, ONNX, Tensorflow, Pytorch
Supported AI Models ResNet50, Yolo V2, GoogleNet V1, MobileNet v1&v2, SSD300, AlexNet, VGG16.etc
H.264 decoder, MJPEG encoder/decoder 1x 1080p @60fps or 2x 1080p @30fps H.264decoder, 75fps for FHD images
Interface USB3.0/USB2.0 slave mode, Type A
USB 9pin (pin width: 1.25mm) interface
Dimensions 38mm x 38mm
Environmental temperature 0 – 40 C (commercial level)
Hot plugin/plugoff Yes
Certification EMC/FCC/3C/CE

Core Advantages

nnm advantage

Power and all data provided over a single USB Type A interface or USB 9pin (pin width: 1.25mm) interface

nnm advantage

Supports DNN/CNN/RNN/LSTM models profiling, compiling and tuning

nnm advantage

Real-time inference in edge device

nnm advantage

Quickly deploy existing DNN/CNN/RNN/LSTM models or uniquely trained networks

nnm advantage

Features Bitmain SophonTM BM1880