通过通道与层联合剪枝，高效压缩CNN模型以适配边缘设备。
Compressing CNN models for resource-constrained systems by channel and layer pruning
- 提出通道与层协同剪枝的混合框架，反向缩小网络规模。
- 在JETSON TX2上模型复杂度显著降低，精度损失极小。
- 适合资源受限的嵌入式AI部署场景，提升推理效率。
卷积神经网络（CNN）在多个领域取得显著突破，但其复杂性和规模急剧增加，给边缘设备部署带来挑战。为此，模型压缩成为关键研究方向，其中剪枝技术尤为突出。本文提出一种结合通道剪枝与层剪枝的混合剪枝框架，受EfficientNet启发——该架构从通道和层两个维度扩展网络，本方法则反向操作，通过剪枝实现网络缩放。实验表明，该方法显著降低模型整体复杂度，相比基线模型仅带来微小精度下降。在NVIDIA JETSON TX2嵌入式AI设备上的部署结果显示，剪枝后模型延迟明显减少，验证了其在资源受限场景下的有效性。
原文摘要 · Abstract (English)
Convolutional Neural Networks (CNNs) have achieved significant breakthroughs in various fields. However, these advancements have led to a substantial increase in the complexity and size of these networks. This poses a challenge when deploying large and complex networks on edge devices. Consequently, model compression has emerged as a research field aimed at reducing the size and complexity of CNNs. One prominent technique in model compression is model pruning. This paper will present a new technique of pruning that combines both channel and layer pruning in what is called a "hybrid pruning framework". Inspired by EfficientNet, a renowned CNN architecture known for scaling up networks from both channel and layer perspectives, this hybrid approach applies the same principles but in reverse, where it scales down the network through pruning. Experiments on the hybrid approach demonstrated a notable decrease in the overall complexity of the model, with only a minimal reduction in accuracy compared to the baseline model. This complexity reduction translates into reduced latency when deploying the pruned models on an NVIDIA JETSON TX2 embedded AI device.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。