IMFMapper PyTorch Model Checkpoint and Shapefiles of IMFs in Crookes and Schomberger A Craters

This dataset contains the PyTorch model checkpoint file (also called the state_dict) of IMFMapper - a DeepLabV3 semantic segmentation Deep Learning model trained to detect impact melt fractures (IMFs) within Lunar Reconnaissance Orbiter Narrow Angle Camera (LROC NAC) imagery of the Moon. Instructions on how to load a model checkpoint in order to re-train or infer it on your own data can be found here. Two .zip files containing the IMFs detected by IMFMapper within two Lunar impact craters (Crookes and Schomberger A) can also be found. These detections are in ESRI shapefile format (named 'cratername_imfs.shp') ready for viewing in GIS software such as QGIS or ArcGIS. We also provide shapefiles outlining the craters themselves (name 'cratername.shp'), as well as the floors and melt ponds within Crookes crater ('crookes_crater_regions.shp').本数据集包含IMFMapper的PyTorch模型权重文件（亦称状态字典state_dict）。IMFMapper是一款基于DeepLabV3的语义分割深度学习模型，专为在月球勘测轨道飞行器窄角相机（Lunar Reconnaissance Orbiter Narrow Angle Camera，LROC NAC）拍摄的月球影像中识别撞击熔体裂隙（Impact Melt Fractures，IMFs）而训练。关于如何加载该模型权重文件以在自有数据上开展重训练或推理的操作说明可在此处查阅。 本数据集同时提供两个压缩包，内含IMFMapper在两个月球撞击坑（克鲁克斯坑（Crookes）与朔姆贝格A坑（Schomberger A））内检测到的IMFs。这些检测结果采用ESRI形状文件格式（命名格式为"cratername_imfs.shp"），可直接在QGIS、ArcGIS等地理信息系统（GIS）软件中加载查看。此外，我们还提供了用于勾勒上述撞击坑轮廓的形状文件（命名格式为"cratername.shp"），以及克鲁克斯坑内的坑底与熔体池轮廓形状文件（"crookes_crater_regions.shp"）。