DSBEC (Dark solitons in BECs dataset)

数据集由带有和不带有孤子激发的玻色-爱因斯坦凝聚物 (bec) 的6257标记图像组成，包括扭结孤子和孤子涡旋。数据集的每个元素都包含2D原子密度的掩蔽图像 (132x164像素)，用于训练在论文 “Bose-Einstein凝聚物中的机器学习增强的暗孤子检测” 中使用的机器学习模型 (https://arxiv.org/abs/2101.05404)，和表示给定图像属于a类的标签 (0表示没有孤子，1表示单个孤子，2表示其他激发)。数据包括数据结构文件和项目描述。该数据集用于训练深度卷积神经网络，以自动识别是否已经在bec中创建了单独的暗孤子，然后在自动孤子检测和定位系统中实现该孤子 (有关详细信息，请参见https://arxiv.org/abs/2101.05404)。

This dataset consists of 6257 labeled images of Bose-Einstein Condensates (BECs) with and without soliton excitations, including kink solitons and soliton vortices. Each sample in the dataset contains a masked 2D atomic density image with a resolution of 132×164 pixels, which is used to train the machine learning models employed in the paper "Machine Learning-Enhanced Dark Soliton Detection in Bose-Einstein Condensates" (https://arxiv.org/abs/2101.05404), as well as labels indicating the category of the corresponding image: 0 denotes no solitons, 1 denotes a single soliton, and 2 denotes other excitations. The dataset includes data structure files and project descriptions. This dataset is utilized to train deep convolutional neural networks to automatically identify whether individual dark solitons have been created in BECs, and deploy the trained models into automatic soliton detection and localization systems. For more details, please refer to https://arxiv.org/abs/2101.05404.

搜集汇总

背景与挑战

背景概述

DSBEC数据集包含6257张标记图像，用于训练机器学习模型检测玻色-爱因斯坦凝聚物中的暗孤子。该数据集提供2D原子密度掩蔽图像及分类标签，支持深度卷积神经网络在自动孤子检测和定位系统中的应用。