ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA
This work addresses model compression for efficient DNN deployment on FPGA devices, offering an incremental improvement over existing multi-precision quantization methods.
The paper tackles DNN quantization for FPGA edge computing by proposing an intra-layer multi-precision method, achieving 70.73% Top1 accuracy on ResNet-18 with ImageNet and a 3.65x speedup in inference time compared to fixed-point quantization.
This work targets the commonly used FPGA (field-programmable gate array) devices as the hardware platform for DNN edge computing. We focus on DNN quantization as the main model compression technique. The novelty of this work is: We use a quantization method that supports multiple precisions along the intra-layer dimension, while the existing quantization methods apply multi-precision quantization along the inter-layer dimension. The intra-layer multi-precision method can uniform the hardware configurations for different layers to reduce computation overhead and at the same time preserve the model accuracy as the inter-layer approach. Our proposed ILMPQ DNN quantization framework achieves 70.73 Top1 accuracy in ResNet-18 on the ImageNet dataset. We also validate the proposed MSP framework on two FPGA devices i.e., Xilinx XC7Z020 and XC7Z045. We achieve 3.65x speedup in end-to-end inference time on the ImageNet, compared with the fixed-point quantization method.