Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.

<em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.</strong></em> <em><strong>Version 3: Updated 2023-04-25</strong></em> These Residual-UNet model data are based on RGB (red, green, and blue) images of coasts and associated labels. Models have been created using Segmentation Gym* using the following dataset**: https://doi.org/10.5281/zenodo.7384242 Classes: {0=other, 1=water} <strong>File descriptions</strong> For each model, there are 5 files with the same root name: 1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse. 2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled. 3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model 4. <strong> '_model_history.npz'</strong> model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py` 5. <strong> '.png'</strong> model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py` Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU <strong>References</strong> *Segmentation Gym: Buscombe, D., &amp; Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym ** Buscombe, D. (2022). Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7384242**Doodleverse/Segmentation Zoo 残差UNet（Res-UNet）模型：用于海岸区域哨兵二号（Sentinel-2）与陆地卫星7/8（Landsat-7/8）的3波段红、绿、蓝（RGB）影像的二分类（水体、其他地物）语义分割** **版本3：2023-04-25更新** 本批残差UNet模型数据基于海岸区域的RGB影像及对应标注标签构建。模型通过Segmentation Gym*工具基于下述数据集**构建完成：https://doi.org/10.5281/zenodo.7384242。类别设置：{0=其他地物，1=水体} **文件说明** 针对每个模型，均包含5个同名根文件，具体如下： 1. **.json格式配置文件**：该文件为Segmentation Gym*创建模型权重文件时所使用的配置文件，包含模型构建、所用数据集信息，以及模型预测的使用方法。该文件简洁实用，掌握该文件即可完全掌握整个Doodleverse工具链。 2. **.h5格式权重文件**：该文件由Segmentation Gym*的`train_model.py`脚本生成，存储了训练完成的模型参数权重，可通过Segmentation Gym*的`seg_images_in_folder.py`脚本调用。支持多模型集成学习。 3. **_modelcard.json格式模型卡片文件**：该JSON文件包含描述模型来源、训练参数及训练数据集的相关字段。该文件与上文提及的配置文件存在部分冗余信息，虽未被程序直接调用，但作为重要的元数据，需与其他模型相关文件一同留存，属于模型套件的组成部分。 4. **_model_history.npz格式模型训练历史文件**：该NumPy归档文件包含训练与验证损失、评估指标的NumPy数组数据，由Segmentation Gym的`train_model.py`脚本生成。 5. **.png格式模型训练损失与平均交并比（mean IoU）曲线文件**：该PNG文件包含模型训练过程中的训练与验证损失曲线、平均交并比得分曲线，为.npz文件中部分数据的可视化结果，由Segmentation Gym的`train_model.py`脚本生成。 此外，BEST_MODEL.txt文件存储了在验证集上取得最优损失与平均交并比的模型名称。 **参考文献** *Segmentation Gym：Buscombe, D., & Goldstein, E. B. (2022). 可复现且可复用的地球科学影像语义分割流水线. 《地球与空间科学》, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 详见：https://github.com/Doodleverse/segmentation_gym ** 训练数据集：Buscombe, D. (2022). 海岸哨兵二号（Sentinel-2）与陆地卫星（Landsat）RGB卫星影像的二分类语义分割数据集（水体、其他地物，v1.0）[数据集]. Zenodo. https://doi.org/10.5281/zenodo.7384242