在大数据量背景下，人工神经网络架构设计的工作量变得又多又重。然而，在这

在大数据量背景下，人工神经网络架构设计的工作量变得又多又重。然而，在这几年兴起了神经网络架构搜索（NAS）方法，在一定搜索空间内可以用NAS自动检索合适的网络模型，这极大地提高了工作效率。本文将展开介绍NAS，并研究使用NAS的EfficientNet和RegNet网络模型对行人服装图像检测识别这一实验，完成检测和分类后，通过调整网络结构和添加注意力机制的方法对该模型进行优化升级。

0/5000

源语言: -

目标语言: -

结果 (英语) 1: [复制]

复制成功！

In the context of large amounts of data, the workload of artificial neural network architecture design has become heavy and heavy. However, in the past few years, the neural network architecture search (NAS) method has emerged. NAS can be used to automatically retrieve a suitable network model in a certain search space, which greatly improves work efficiency. This article will introduce NAS, and study the experiment of using NAS's EfficientNet and RegNet network models to detect and recognize pedestrian clothing images. After the detection and classification are completed, the model will be optimized and upgraded by adjusting the network structure and adding attention mechanisms.

正在翻译中..

结果 (英语) 2:[复制]

复制成功！

Against the background of large data volume, the workload of artificial neural network architecture design becomes more and more heavy. However, in recent years, the emergence of neural network architecture search (NAS) method, in a certain search space can be used to automatically retrieve the appropriate network model, which greatly improves the efficiency of work. This paper will introduce NAS, and study the use of NAS EfficientNet and RegNet network model for pedestrian clothing image detection and recognition of the experiment, after the completion of detection and classification, by adjusting the network structure and adding attention mechanism to optimize the model upgrade.

正在翻译中..

结果 (英语) 3:[复制]

复制成功！

In the context of large amount of data, the workload of artificial neural network architecture design becomes more and more heavy. However, in recent years, the rise of neural network architecture search (NAS) method, in a certain search space can use NAS to automatically retrieve the appropriate network model, which greatly improves the work efficiency. This paper will introduce NAS, and study the experiment of pedestrian clothing image detection and recognition using the efficientnet and regnet network model of NAS. After the detection and classification, the model is optimized and upgraded by adjusting the network structure and adding attention mechanism.

正在翻译中..

其它语言

本翻译工具支持: 世界语, 丹麦语, 乌克兰语, 乌兹别克语, 乌尔都语, 亚美尼亚语, 伊博语, 俄语, 保加利亚语, 信德语, 修纳语, 僧伽罗语, 克林贡语, 克罗地亚语, 冰岛语, 加利西亚语, 加泰罗尼亚语, 匈牙利语, 南非祖鲁语, 南非科萨语, 卡纳达语, 卢旺达语, 卢森堡语, 印地语, 印尼巽他语, 印尼爪哇语, 印尼语, 古吉拉特语, 吉尔吉斯语, 哈萨克语, 土库曼语, 土耳其语, 塔吉克语, 塞尔维亚语, 塞索托语, 夏威夷语, 奥利亚语, 威尔士语, 孟加拉语, 宿务语, 尼泊尔语, 巴斯克语, 布尔语(南非荷兰语), 希伯来语, 希腊语, 库尔德语, 弗里西语, 德语, 意大利语, 意第绪语, 拉丁语, 拉脱维亚语, 挪威语, 捷克语, 斯洛伐克语, 斯洛文尼亚语, 斯瓦希里语, 旁遮普语, 日语, 普什图语, 格鲁吉亚语, 毛利语, 法语, 波兰语, 波斯尼亚语, 波斯语, 泰卢固语, 泰米尔语, 泰语, 海地克里奥尔语, 爱尔兰语, 爱沙尼亚语, 瑞典语, 白俄罗斯语, 科西嘉语, 立陶宛语, 简体中文, 索马里语, 繁体中文, 约鲁巴语, 维吾尔语, 缅甸语, 罗马尼亚语, 老挝语, 自动识别, 芬兰语, 苏格兰盖尔语, 苗语, 英语, 荷兰语, 菲律宾语, 萨摩亚语, 葡萄牙语, 蒙古语, 西班牙语, 豪萨语, 越南语, 阿塞拜疆语, 阿姆哈拉语, 阿尔巴尼亚语, 阿拉伯语, 鞑靼语, 韩语, 马其顿语, 马尔加什语, 马拉地语, 马拉雅拉姆语, 马来语, 马耳他语, 高棉语, 齐切瓦语, 等语言的翻译.