Datasets from "A new method for the detection of siliceous microfossils on sediment microscope slides using convolutional neural networks". JGR Biogeosciences.

This repository contains the datasets linked to "A new method for the detection of siliceous microfossils on sediment microscope slides using convolutional neural networks" (Journal of Geophysical Research: Biogeosciences, https://doi.org/10.1029/2024JG008047). This includes: The images and annotation* text files (in YOLO format) used for the detection of siliceous microfossils. The models and training results for the trainings presented in the main text and supporting information. *Note that while annotations were attributed to 14 general categories, only twelve of these were used during training (i.e. Pennate, Centric, Silicoflagellate, Centric_debris, Spore, Other_Biomin, Cocco, Silicoflagellate_debris, Undetermined_silica, Chateoceros_Bacteriastrum, Calcispheres, Foraminifer), and all were pooled into a single "Microfossil" category for the purpose of the training.本存储库包含与《利用卷积神经网络（Convolutional Neural Networks）检测沉积显微镜载玻片上的硅质微化石（siliceous microfossils）》（发表于《Journal of Geophysical Research: Biogeosciences》，DOI: 10.1029/2024JG008047）相关的数据集。具体内容如下： 1. 用于硅质微化石检测的图像与标注文本文件（采用YOLO（You Only Look Once）格式）。 2. 正文及补充材料中所述训练任务对应的模型与训练结果。 *注：尽管标注共涵盖14个通用类别，但训练过程中仅使用其中12类，分别为：羽纹硅藻（Pennate）、中心硅藻（Centric）、硅鞭毛虫（Silicoflagellate）、中心硅藻残骸（Centric_debris）、孢子（Spore）、其他生物矿物（Other_Biomin）、球石藻（Cocco）、硅鞭毛虫残骸（Silicoflagellate_debris）、未确定硅质体（Undetermined_silica）、角刺藻-链状藻属（Chateoceros_Bacteriastrum）、钙球（Calcispheres）、有孔虫（Foraminifer）；且为训练需求，所有类别均被合并为单一的"微化石（Microfossil）"类别。