plot_results is also useful for plotting annotations. Sometimes I worry that we should have named it something more general. When you use it to plot annotations, you don't yet have scores, and there isn't any reason you need them. Just add a except for this case and add a dummy score.
split_files = split_raster(df, path_to_raster="/orange/ewhite/DeepForest/Araujo_2020/Orthomosaic_WGS84_UTM20S.tif", root_dir="/orange/ewhite/DeepForest/Araujo_2020/",
base_dir="/orange/ewhite/DeepForest/Araujo_2020/crops/", patch_size=2000, patch_overlap=0)
for image in split_files.image_path.unique():
image_df = split_files[split_files.image_path==image]
image_df.root_dir = "/orange/ewhite/DeepForest/Araujo_2020/crops/"
plot_results(image_df)
plot_results is also useful for plotting annotations. Sometimes I worry that we should have named it something more general. When you use it to plot annotations, you don't yet have scores, and there isn't any reason you need them. Just add a except for this case and add a dummy score.