A General Neural Network Deployment Framework for Edge Devices

As the expansion of edge devices, such as local servers or even IoT (Internet Things) computing reforms data processing flow, engendering improvement in faster insights, improved response times and better bandwidth availability. However, industry encounters computational resource constraints machine learning on e.g., limitation memory power. To tackle this situation, we attempt to enhance flexibility neural network models for variable hardware constraints. In paper, propose a paradigm combination implementation primitive solution; further more, manage build up general deployment framework devices.