The widening gap between processor and memory speeds makes cache an important issue in the computer system design. Compared with work set of programs, cache resource is often rare. Therefore, it is very important for ...The widening gap between processor and memory speeds makes cache an important issue in the computer system design. Compared with work set of programs, cache resource is often rare. Therefore, it is very important for a computer system to use cache efficiently. Toward a dynamically reconfigurable cache proposed recently, DOOC （Data- Object Oriented Cache）, this paper proposes a quantitative framework for analyzing the cache requirement of data-objects, which includes cache capacity, block size, associativity and coherence protocol. And a kind of graph coloring algorithm dealing with the competition between data-objects in the DOOC is proposed as well. Finally, we apply our approaches to the compiler management of DOOC. We test our approaches on both a single-core platform and a four-core platform. Compared with the traditional caches, the DOOC in both platforms achieves an average reduction of 44.98% and 49.69% in miss rate respectively. And its performance is very close to the ideal optimal cache.展开更多
为了降低柚子等水果目标检测对大量标注数据的依赖,本文提出了一种融合视觉语言模型的柚子分形树图像生成增强方法。该方法仅需3~5幅无标注真实图像,即可在无训练条件下生成大规模带标注的训练数据集。首先利用基于文本提示的零样本分...为了降低柚子等水果目标检测对大量标注数据的依赖,本文提出了一种融合视觉语言模型的柚子分形树图像生成增强方法。该方法仅需3~5幅无标注真实图像,即可在无训练条件下生成大规模带标注的训练数据集。首先利用基于文本提示的零样本分割模型(Grounded segment anything model,Grounded SAM)提取柚树组件,然后结合稳定扩散模型Stable Diffusion使用文本提示生成随机背景,最后使用改进的分形树算法生成柚树以提升多样性及真实感。试验采用YOLO v10轻量化版本进行验证,在自建的非结构化环境柚子目标检测数据集上,当训练集真实图像数量分别为0、8、16、32、64幅时,使用本文方法后模型多阈值平均精度均值(Mean average precision at intersection over union thresholds from 0.50 to 0.95,mAP50-95)提升率依次达到662.3%、24.9%、13.7%、8.8%、1.8%。当训练集中真实图像数量为221幅,生成图像数量为512幅时,模型达到最优性能:精确率为76.9%,召回率为62.7%,mAP50为70.3%,mAP50-95为38.4%。迁移到橙子目标检测任务,相同数据规模下的性能提升分别为212.9%、16.5%、14.0%、5.2%、4.1%。当训练集中真实图像数量为1302幅,生成图像数量为512幅时,模型同样达到最优性能:精确率为90.3%,召回率为87.8%,mAP50为94.0%,mAP50-95为54.0%。试验结果表明,该图像生成增强方法在零样本和少样本学习场景中能够有效扩展训练数据,提高YOLO v10轻量化版本目标检测的性能,并展现出良好的泛化能力。展开更多
传统的航空器适航质量特性优化方法依赖单一数据源,无法应对多特性耦合的复杂场景。因此,开展基于多源数据驱动的航空器适航质量特性优化设计研究。采用皮尔逊相关系数和多元回归分析揭示特性间关联规律,构建“结构-系统-环境”耦合关...传统的航空器适航质量特性优化方法依赖单一数据源,无法应对多特性耦合的复杂场景。因此,开展基于多源数据驱动的航空器适航质量特性优化设计研究。采用皮尔逊相关系数和多元回归分析揭示特性间关联规律,构建“结构-系统-环境”耦合关联矩阵。以结构合规性、系统可靠性和成本可控性为目标,利用改进的非支配排序遗传算法(Non-dominated Sorting Genetic Algorithm-Ⅱ,NSGA-Ⅱ)对机翼蒙皮厚度等核心变量进行多目标优化,从而完成适航特性优化设计。实例分析显示,应用该方法后,航电系统电压波动系数降低50.6%,航电系统平均故障间隔时间(Mean Time Between Failures,MTBF)提高25.0%,液压系统密封件更换周期延长33.3%,机翼最大挠度与发动机振动加速度有效值分别优化11.2%和21.6%,实现了航空器适航质量特性的全局提升。展开更多
基金supported in part by the National Natural Science Foundation of China under Grant Nos.60621003,60873014.
文摘The widening gap between processor and memory speeds makes cache an important issue in the computer system design. Compared with work set of programs, cache resource is often rare. Therefore, it is very important for a computer system to use cache efficiently. Toward a dynamically reconfigurable cache proposed recently, DOOC （Data- Object Oriented Cache）, this paper proposes a quantitative framework for analyzing the cache requirement of data-objects, which includes cache capacity, block size, associativity and coherence protocol. And a kind of graph coloring algorithm dealing with the competition between data-objects in the DOOC is proposed as well. Finally, we apply our approaches to the compiler management of DOOC. We test our approaches on both a single-core platform and a four-core platform. Compared with the traditional caches, the DOOC in both platforms achieves an average reduction of 44.98% and 49.69% in miss rate respectively. And its performance is very close to the ideal optimal cache.
文摘为了降低柚子等水果目标检测对大量标注数据的依赖,本文提出了一种融合视觉语言模型的柚子分形树图像生成增强方法。该方法仅需3~5幅无标注真实图像,即可在无训练条件下生成大规模带标注的训练数据集。首先利用基于文本提示的零样本分割模型(Grounded segment anything model,Grounded SAM)提取柚树组件,然后结合稳定扩散模型Stable Diffusion使用文本提示生成随机背景,最后使用改进的分形树算法生成柚树以提升多样性及真实感。试验采用YOLO v10轻量化版本进行验证,在自建的非结构化环境柚子目标检测数据集上,当训练集真实图像数量分别为0、8、16、32、64幅时,使用本文方法后模型多阈值平均精度均值(Mean average precision at intersection over union thresholds from 0.50 to 0.95,mAP50-95)提升率依次达到662.3%、24.9%、13.7%、8.8%、1.8%。当训练集中真实图像数量为221幅,生成图像数量为512幅时,模型达到最优性能:精确率为76.9%,召回率为62.7%,mAP50为70.3%,mAP50-95为38.4%。迁移到橙子目标检测任务,相同数据规模下的性能提升分别为212.9%、16.5%、14.0%、5.2%、4.1%。当训练集中真实图像数量为1302幅,生成图像数量为512幅时,模型同样达到最优性能:精确率为90.3%,召回率为87.8%,mAP50为94.0%,mAP50-95为54.0%。试验结果表明,该图像生成增强方法在零样本和少样本学习场景中能够有效扩展训练数据,提高YOLO v10轻量化版本目标检测的性能,并展现出良好的泛化能力。
文摘传统的航空器适航质量特性优化方法依赖单一数据源,无法应对多特性耦合的复杂场景。因此,开展基于多源数据驱动的航空器适航质量特性优化设计研究。采用皮尔逊相关系数和多元回归分析揭示特性间关联规律,构建“结构-系统-环境”耦合关联矩阵。以结构合规性、系统可靠性和成本可控性为目标,利用改进的非支配排序遗传算法(Non-dominated Sorting Genetic Algorithm-Ⅱ,NSGA-Ⅱ)对机翼蒙皮厚度等核心变量进行多目标优化,从而完成适航特性优化设计。实例分析显示,应用该方法后,航电系统电压波动系数降低50.6%,航电系统平均故障间隔时间(Mean Time Between Failures,MTBF)提高25.0%,液压系统密封件更换周期延长33.3%,机翼最大挠度与发动机振动加速度有效值分别优化11.2%和21.6%,实现了航空器适航质量特性的全局提升。
