Make anthropogenic example work

Author: GwenaelleSa

examples/anthropogenic-activities/config_trne.yaml

@@ -5,7 +5,7 @@ prepare_data.py:
     fp_shapefile: data/FP_labels.gpkg               # FP labels
     # empty_tiles_aoi: data/AoI/<AOI_SHPFILE>           # AOI in which additional empty tiles can be selected. Only one 'empty_tiles' option can be selected  
     # empty_tiles_year: 2023                              # If "empty_tiles_aoi" selected then provide a year. Choice: (1) numeric (i.e. 2020), (2) [year1, year2] (random selection of a year within a given year range) 
-    empty_tiles_shp: data/20240726_EPT.gpkg    # Provided shapefile of selected empty tiles. Only one 'empty_tiles' option can be selected                     
+    empty_tiles_shp: data/20250924_ept_tiles.gpkg    # Provided shapefile of selected empty tiles. Only one 'empty_tiles' option can be selected                     
     category_field: Classe
   output_folder: output/trne/
   zoom_level: 16 
@@ -16,11 +16,12 @@ generate_tilesets.py:
     enable: False  # sample of tiles
     nb_tiles_max: 2000
   working_directory: .
+  output_folder: output/trne/
   datasets:
     aoi_tiles: output/trne/tiles.geojson
     ground_truth_labels: output/trne/labels.geojson
-    fp_labels:             # Uncomment if FP shapefile exists in prepare_data.py     
-      fp_shp: output/trne/FP.geojson
+    add_fp_labels:             # Uncomment if FP shapefile exists in prepare_data.py     
+      fp_labels: output/trne/FP.geojson
       frac_trn: 0.7        # fraction of fp tiles to add to the trn dataset, then the remaining tiles will be split in 2 and added to tst and val datasets
     image_source:
       type: XYZ                             # supported values: 1. MIL = Map Image Layer 2. WMS 3. XYZ 4. FOLDER
@@ -30,7 +31,6 @@ generate_tilesets.py:
     tiles_frac: 0.5       # fraction (relative to the number of tiles intersecting labels) of empty tiles to add
     frac_trn: 0.7         # fraction of empty tiles to add to the trn dataset, then the remaining tiles will be split in 2 and added to tst and val datasets
     keep_oth_tiles: False # keep tiles in oth dataset not intersecting oth labels
-  output_folder: output/trne/
   tile_size: 256      # per side, in pixels
   overwrite: True
   n_jobs: 10

examples/anthropogenic-activities/data/20240726_EPT.gpkg renamed to examples/anthropogenic-activities/data/20250924_emtpy_tiles.gpkg

@@ -214,10 +214,11 @@ def download_tiles(datasets_dict, gt_labels_gdf, oth_labels_gdf, fp_labels_gdf,
             OTH_TILES = empty_tiles_dict['keep_oth_tiles'] if 'keep_oth_tiles' in empty_tiles_dict.keys() else True
 
             logger.info('Adding empty tiles to the datasets...')
-            tmp_gdf = aoi_tiles_gdf.copy()
-            tmp_gdf = tmp_gdf[~tmp_gdf['id'].isin(id_list_gt_tiles)] if GT_LABELS else tmp_gdf
-            tmp_gdf = tmp_gdf[~tmp_gdf['id'].isin(id_list_fp_tiles)] if FP_LABELS else tmp_gdf
-            all_empty_tiles_gdf = tmp_gdf[~tmp_gdf['id'].isin(id_list_oth_tiles)] if OTH_LABELS else tmp_gdf
+            label_tiles = \
+                (id_list_gt_tiles if GT_LABELS else [])\
+                + (id_list_fp_tiles if FP_LABELS else [])\
+                + (id_list_oth_tiles if OTH_LABELS else [])
+            all_empty_tiles_gdf = aoi_tiles_gdf[~aoi_tiles_gdf['id'].isin(label_tiles)].copy()
 
             nb_gt_tiles = len(id_list_gt_tiles) if GT_LABELS else 0
             nb_fp_tiles = len(id_list_fp_tiles) if FP_LABELS else 0

helpers/download_tiles.py

@@ -189,14 +189,14 @@ def find_category(df):
     if 'category' in df.columns:
         df.rename(columns={'category': 'CATEGORY'}, inplace = True)
     elif 'CATEGORY' not in df.columns:
-        logger.critical('The GT labels have no category. Please produce a CATEGORY column when preparing the data.')
+        logger.critical('The labels have no category. Please produce a CATEGORY column when preparing the data.')
         sys.exit(1)
 
     if 'supercategory' in df.columns:
         df.rename(columns={'supercategory': 'SUPERCATEGORY'}, inplace = True)
     elif 'SUPERCATEGORY' not in df.columns:
-        logger.critical('The GT labels have no supercategory. Please produce a SUPERCATEGORY column when preparing the data.')
-        sys.exit(1)
+        logger.warning('The labels have no supercategory. A standard "foo" supercategory will be assigned.')
+        df['SUPERCATEGORY'] = 'foo'
 
     return df
 

helpers/misc.py

@@ -124,10 +124,10 @@ def main(cfg_file_path):
 
     # Get label info if available
     GT_LABELS = DATASETS['ground_truth_labels'] if 'ground_truth_labels' in DATASETS.keys() else None
-    OTH_LABELS = DATASETS['other_labels'] if 'other_labels' in DATASETS.keys() else None
+    OTH_LABELS = DATASETS['other_labels'] if 'other_labels' in DATASETS.keys() else None            # Labels that are not good enough to be used for training
 
     # Choose to add emtpy and FP tiles
-    ADD_EMPTY_TILES = cfg['add_empty_tiles'] if 'add_empty_tiles' in cfg.keys() else False          # Selected from oth tiles
+    EMPTY_TILES_DICT = cfg['empty_tiles'] if 'empty_tiles' in cfg.keys() else False          # Selected from oth tiles
     ADD_FP_LABELS = DATASETS['add_fp_labels'] if 'add_fp_labels' in DATASETS.keys() else False      # Determine FP tiles based on FP labels
     if ADD_FP_LABELS:
         FP_LABELS = ADD_FP_LABELS['fp_labels']
@@ -178,13 +178,13 @@ def main(cfg_file_path):
 
     # ------ Tile download
     aoi_tiles_gdf, img_metadata_dict, id_list_ept_tiles, dt_written_files = download_tiles(
-        DATASETS, gt_labels_gdf, oth_labels_gdf, fp_labels_gdf, ADD_EMPTY_TILES, TILE_SIZE, N_JOBS, OUTPUT_DIR, DEBUG_MODE, DEBUG_MODE_LIMIT, OVERWRITE
+        DATASETS, gt_labels_gdf, oth_labels_gdf, fp_labels_gdf, EMPTY_TILES_DICT, TILE_SIZE, N_JOBS, OUTPUT_DIR, DEBUG_MODE, DEBUG_MODE_LIMIT, OVERWRITE
     )
     written_files.extend(dt_written_files)
 
     # ------ Split tiles between training/validation/test/other
     split_aoi_tiles_with_img_md_gdf, st_written_files = split_tiles(
-        aoi_tiles_gdf, gt_labels_gdf, oth_labels_gdf, fp_labels_gdf, FP_FRAC_TRN, ADD_EMPTY_TILES, id_list_ept_tiles, img_metadata_dict, TILE_SIZE, SEED, 
+        aoi_tiles_gdf, gt_labels_gdf, oth_labels_gdf, fp_labels_gdf, FP_FRAC_TRN, EMPTY_TILES_DICT, id_list_ept_tiles, img_metadata_dict, TILE_SIZE, SEED, 
         OUTPUT_DIR, DEBUG_MODE
     )
     written_files.extend(st_written_files)