SOPHGO AI Micro Server SE7 32-EA4 equipped with the 4th generation AI SoC BM1684X, boasts high performance, low power consumption, and excellent environmental adaptability. By pairing it with diverse deep learning algorithms, it enables applications such as video structuring, face recognition, behavior analysis, and status monitoring. It also realizes AI empowerment at the edge side in various fields such as smart cities, intelligent transportation, smart energy, financial technology, telecommunication, and smart industry
Supports up to 32TOPS INT8 peak computing power, or 16TOPS FP16/BF16 half-precision computing power, or 2TOPS FP32 high-precision computing power.
Supports up to 32 channels of 1080P HD video full-process handling, and supports 32 channels of full HD video hardware decoding and 12 channels of encoding.
Supports mainstream deep learning frameworks such as Caffe/ TensorFlow/ PyTorch/ MXNet/ PaddlePaddle/ ONNX/ Darknet.
Supports active fan cooling and wide operating temperature range from -20℃ to +60℃.
Supports a variety of algorithm porting, such as human/vehicle/non-object recognition, video structuring, trajectory behavior analysis.
Supports flexible deployment in multiple domains and scenarios such as smart parks, security, industrial control, and commerce.
Supports multiple interfaces such as USB, HDMI, RS-485, RS-232, SATA. and etc.
Optional Add-on: 4G(Mini PCIe)/5G(M.2)/SSD(M.2,SATA 3.0,2242)
Video stream and image stream recognition, video structure analysis, trajectory analysis, etc.
Checkpoint, automatic vechicle identification, law enforcement assistance, smart parking
Face recognition security checking, staff attendance management, smart alart system
Goods recognition, smart stores application, face recongnization payment
BMNNSDK (BITMAIN Neural Network SDK) one-stop toolkit provides a series of software tools including the underlying driver environment, compiler and inference deployment tool. The easy-to-use and convenient toolkit covers the model optimization, efficient runtime support and other capabilities required for neural network inference. It provides easy-to-use and efficient full-stack solutions for the development and deployment of deep learning applications. BMNNSDK minimizes the development cycle and cost of algorithms and software. Users can quickly deploy deep learning algorithms on various AI hardware products of SOPHGO to facilitate intelligent applications.
chip
model
SOPHON BM1684X
CPU
8-core A53@2.3GHz
AI Performance
INT8
Peak performance 32TOPS
FP16/BF16
Peak performance 16TFLOPS
FP32
Peak performance 2TFLOPS
Video / Picture codec
Video decoding capability
800fps 1080p (32 channels 1080P @ 25FPS)
Video encoding capability
300fps 1080p (12 channels 1080P @ 25FPS)
Picture codec capability
600 PCS / s 1080p
Memory and storage
Memory
16GB
eMMC
64GB
External interface
Ethernet interface
10/100 / 1000Mbps adaptive * 2
USB
USB3.0 *2、USB2.0 *2
Storage
MicroSD *1
Display
HDMI *1
Wireless
WiFi/BT
Serial port
RS-232 *1 / RS-485 *1
Mechanical
Length * width * height
210mm*130mm*44.5mm
Power supply and power consumption
Power supply
DC 12V
Typicalpower consumption
≤20W
Temperature and humidity
Working temperature
-20 ℃ ~ + 60 ℃
Humidity
10% ~ 90%RH, no condensation
Other functions
Optional
SATA HDD (internal, 2242 SSD is expendable)
4G/5G (new backplane and more antennas are needed)