An FPGA-Based Accelerator Enabling Efficient Support for CNNs with Arbitrary Kernel Sizes

arXiv:2402.14307v1 Announce Type: cross
Abstract: Convolutional neural networks (CNNs) with large kernels, drawing inspiration from the key operations of vision transformers (ViTs), have demonstrated impressive performance in various vision-based applications. To address the issue of computational efficiency degradation in existing designs for supporting large-kernel convolutions, an FPGA-based inference accelerator is proposed for the efficient deployment of CNNs with arbitrary kernel sizes. Firstly, a Z-flow method is presented to optimize the computing data flow by maximizing data reuse opportunity. Besides, the …

abstract accelerator applications arxiv cnns computational convolutional neural networks cs.ar cs.lg designs efficiency enabling fpga inference inspiration issue kernel key networks neural networks operations performance support the key transformers type vision vision transformers