Design of MobileNetV3 network accelerator based on dynamic adaptive computing engine

Existing acceleration methods for efficient and lightweight MobileNetV3 networks usually use highly customized computing engines for model calculations, which limits the scalability of the accelerator and makes it only applicable to small networks or resource-rich hardware platforms. To address this problem, this paper proposes a MobileNetV3 network accelerator based on a dynamic adaptive computing engine. Firstly, a pipeline inference architecture of local perception area convolution is designed to achieve highly parallel processing and buffer scheduling of features and weights. Secondly, a global adaptive point convolution method is proposed to optimize point convolution and combine spatial exploration to obtain the optimal parameter configuration to achieve maximum computational parallelism. In addition, the accelerator can be dynamically configured according to model parameter changes to adapt to different scenarios. Experimental results show that the accelerator's inference speed is 8 F/s, which is 2.7 times as fast as existing methods.