add columns to clean

data_prep/collect_tasks.py

@@ -88,6 +88,17 @@
 TreePolygons_datasets["filename"] = TreePolygons_datasets["filename"].apply(os.path.basename)
 
 # Save splits
+
+# Clean the columns
+Boxes_columns = ["xmin","ymin","xmax","ymax","filename","split","source","resolution"]
+TreeBoxes_datasets = TreeBoxes_datasets[Boxes_columns]
+
+Polygons_columns = ["polygon","filename","split","source","resolution"]
+TreePolygons_datasets = TreePolygons_datasets[Polygons_columns]
+
+Points_columns = ["x","y","filename","split","source","resolution"]
+TreePoints_datasets = TreePoints_datasets[Points_columns]
+
 TreePolygons_datasets.to_csv("/orange/ewhite/DeepForest/MillionTrees/TreePolygons_v0.0/official.csv", index=False)
 TreePoints_datasets.to_csv("/orange/ewhite/DeepForest/MillionTrees/TreePoints_v0.0/official.csv", index=False)
 TreeBoxes_datasets.to_csv("/orange/ewhite/DeepForest/MillionTrees/TreeBoxes_v0.0/official.csv", index=False)

docs/dataset_structure.md

@@ -1,5 +1,4 @@
 # Dataset structure
 
 The organization of this dataset was inspired by the WILDS benchmark and torchgeo python package.
-
-
+There are three overarching datasets. 'Points', 'Polygons' and 'Boxes' based on the annotation geometry. See (datasets)[datasets.md] for the coponent

docs/datasets.md

@@ -22,7 +22,6 @@ Location: Southern California, United States
 
 <img src="public/Ventura.png" alt="sample_image" style="width:300px; height:auto;">
 
-
 ## Boxes
 
 ### Velasquez-Camacho et al. 2023
@@ -79,7 +78,7 @@ https://zenodo.org/records/8136161
 
 Location: Danum, Malaysia
 
-## Wagner et al. 2023
+### Wagner et al. 2023
 
 https://www.mdpi.com/2504-446X/7/3/155