Dynamically Reconfigurable Deep Learning for Efficient Video Processing in Smart IoT Systems (original) (raw)
2020
Abstract
Video systems are the core of many IoT systems, and efficient processing is crucial for their operation. There is little work focusing on the flexibility of current hardware systems when used for long term deployment, particularly for constrained devices such as those used in IoT. This paper shows a unique case study for Video Processing Nodes that adopt deep learning algorithms and dynamically switch the models within a streaming path to investigate the flexibility that can be offered and the limitations within different applications. The video processing node utilizes a framework called FINN that generates FPGA compatible models. The proposed system can switch between different configurations according to their quantization, showing how accuracy and confidence can vary with each option. Inference per second is one of the major benefits when switching between different configurations, where a 1-bit weight and 1-bit activation achieves the highest inference rate for convolutional neural networks and greatly reduces energy consumption.
Kasem Khalil hasn't uploaded this paper.
Let Kasem know you want this paper to be uploaded.
Ask for this paper to be uploaded.