Iterative Filter Pruning for Concatenation-based CNN Architectures

TL;DR

This paper introduces a novel iterative filter pruning method tailored for concatenation-based CNN architectures like YOLOv7, significantly reducing model size and computational cost while maintaining accuracy, enabling real-time deployment on edge devices.

Contribution

The paper presents a new pruning approach that handles concatenation layers in CNNs, automates sensitivity analysis, and demonstrates effective deployment on FPGA and NVIDIA Jetson Xavier AGX.

Findings

2x speedup in convolutional layer processing

Real-time performance of 14 FPS on FPGA

Significant reduction in model parameters and FLOPs

Abstract

Model compression and hardware acceleration are essential for the resource-efficient deployment of deep neural networks. Modern object detectors have highly interconnected convolutional layers with concatenations. In this work, we study how pruning can be applied to such architectures, exemplary for YOLOv7. We propose a method to handle concatenation layers, based on the connectivity graph of convolutional layers. By automating iterative sensitivity analysis, pruning, and subsequent model fine-tuning, we can significantly reduce model size both in terms of the number of parameters and FLOPs, while keeping comparable model accuracy. Finally, we deploy pruned models to FPGA and NVIDIA Jetson Xavier AGX. Pruned models demonstrate a 2x speedup for the convolutional layers in comparison to the unpruned counterparts and reach real-time capability with 14 FPS on FPGA. Our code is available at https://github.com/fzi-forschungszentrum-informatik/iterative-yolo-pruning.