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 this https URL.
Abstract (translated)
模型压缩和硬件加速对深度神经网络的资源高效部署至关重要。现代目标检测器具有高度互联的卷积层，并具有连接。在这项工作中，我们研究了如何应用于这种架构，以实现YOLOv7的资源高效部署。我们提出了一种处理连接层的方法，基于卷积层的连接图。通过自动处理迭代敏感分析、剪枝和后续模型微调，我们可以显著降低模型的大小，无论是参数数量还是FLOPs，同时保持竞争力的模型精度。最后，我们将修剪后的模型部署到FPGA和NVIDIA Jetson Xavier AGX。修剪后的模型在卷积层方面表现出与未修剪相比的2倍速度提升，并在FPGA上达到14 FPS的实时性能。我们的代码可在此处访问：https://www.things.int/https://www.things.int/
URL
https://arxiv.org/abs/2405.03715
