● Support simultaneous processing of 16 1080P@30fps H.264/H.265 real-time streams or stored streams.
● A special gas pedal for deep learning that uses a combination of front-end image pre-processing and back-end algorithm computing to support low-bit quantization of CNN, RCNN and other neural network structures, low-bit quantization of AlexNet, VGG, ResNet and other classification neural networks, low-bit quantization of Faster R-CNN, SSD, FPN and other target detection neural networks.
●Support mainstream deep learning frameworks such as TensorFlow, Caffe and Pytorch, and support face detection, tracking and recognition algorithms.
● Support dual gigabit network ports and expandable 4G/WIFI wireless network mode.
● Low power consumption design, combined with shell heat dissipation, can increase the cooling fan active cooling, the product is stable and reliable.
●Fully embedded structure, highly integrated, can support desktop placement or wall mounting, very easy to install and maintain.