Although convolutional neural networks (CNNs) have been widely applied in various cognitive applications, they are still very computationally intensive for resource-constrained mobile systems. To reduce the resource consumption of CNN computation, many optimization works have been proposed for mobile CNN deployment. However, most works are merely targeting CNN model compression from the perspective of parameter size or model structure, ignoring different resource constraints in mobile systems with respect to memory, energy, and real-time requirement. Moreover, previous works take accuracy as their primary consideration, requiring a time-costing retraining process to compensate the inference accuracy loss after compression. To address these issues, we propose DiReCtX—a dynamic resource-aware CNN model reconfiguration framework. DiReCtX is based on a set of accurate CNN profiling models for different resource consumption and inference accuracy estimation. With manageable consumption/accuracy tradeoffs, DiReCtX can reconfigure a CNN model to meet distinct resource constraint types and levels with expected inference performance maintained. To further achieve fast model reconfiguration in real-time, improved CNN model pruning and its corresponding accuracy tuning strategies are also proposed in DiReCtX. The experiments show that the proposed CNN profiling models can achieve 94.6% and 97.1% accuracy for CNN model resource consumption and inference accuracy estimation. Meanwhile, the proposed reconfiguration scheme of DiReCtX can achieve at most 44.44% computation acceleration, 31.69% memory reduction, and 32.39% energy saving, respectively. On field-tests with state-of-the-art smartphones, DiReCtX can adapt CNN models to various resource constraints in mobile application scenarios with optimal real-time performance.

中文翻译：

---

DiReCtX：用于实时移动应用程序的动态资源感知 CNN 重新配置框架

尽管卷积神经网络 (CNN) 已广泛应用于各种认知应用，但对于资源受限的移动系统而言，它们的计算量仍然很高。为了减少CNN计算的资源消耗，已经提出了许多针对移动CNN部署的优化工作。然而，大多数工作只是从参数大小或模型结构的角度针对 CNN 模型压缩，而忽略了移动系统中在内存、能量和实时要求方面的不同资源约束。此外，以前的工作以准确性为主要考虑因素，需要一个耗时的重新训练过程来补偿压缩后的推理准确性损失。为了解决这些问题，我们提出了 DiReCtX——一种动态资源感知 CNN 模型重构框架。DiReCtX 基于一组精确的 CNN 分析模型，用于不同的资源消耗和推理精度估计。通过可管理的消耗/准确性权衡，DiReCtX 可以重新配置 CNN 模型以满足不同的资源约束类型和级别，同时保持预期的推理性能。为了进一步实现实时快速模型重构，DiReCtX 还提出了改进的 CNN 模型剪枝及其相应的精度调整策略。实验表明，所提出的 CNN 分析模型在 CNN 模型资源消耗和推理精度估计方面可以达到 94.6% 和 97.1% 的准确率。同时，提出的 DiReCtX 重构方案最多可实现 44.44% 的计算加速、31.69% 的内存减少和 32.39% 的节能。