megadetector 5.0.29__py3-none-any.whl → 10.0.0__py3-none-any.whl

megadetector/data_management/remap_coco_categories.py

@@ -2,7 +2,9 @@
 
 remap_coco_categories.py
 
-Given a COCO-formatted dataset, remap the categories to a new mapping.
+Given a COCO-formatted dataset, remap the categories to a new mapping.  A common use
+case is to take a fine-grained dataset (e.g. with species-level categories) and
+map them to coarse categories (typically MD categories).
 
 """
 
@@ -10,6 +12,7 @@ Given a COCO-formatted dataset, remap the categories to a new mapping.
 
 import os
 import json
+import argparse
 
 from copy import deepcopy
 from megadetector.utils.ct_utils import invert_dictionary
@@ -29,9 +32,9 @@ def remap_coco_categories(input_data,
     Args:
         input_data (str or dict): a COCO-formatted dict or a filename.  If it's a dict, it will
             be copied, not modified in place.
-        output_category_name_to_id (dict) a dict mapping strings to ints.  Categories not in
+        output_category_name_to_id (dict): a dict mapping strings to ints.  Categories not in
             this dict will be ignored or will result in errors, depending on allow_unused_categories.
-        input_category_name_to_output_category_name: a dict mapping strings to strings.
+        input_category_name_to_output_category_name (dict): a dict mapping strings to strings.
             Annotations using categories not in this dict will be omitted or will result in
             errors, depending on allow_unused_categories.
         output_file (str, optional): output file to which we should write remapped COCO data
@@ -130,4 +133,63 @@ def remap_coco_categories(input_data,
 
 #%% Command-line driver
 
-# TODO
+def main():
+    """
+    Command-line interface to remap COCO categories.
+    """
+
+    parser = argparse.ArgumentParser(
+        description='Remap categories in a COCO-formatted dataset'
+    )
+    parser.add_argument(
+        'input_coco_file',
+        type=str,
+        help='Path to the input COCO .json file'
+    )
+    parser.add_argument(
+        'output_category_map_file',
+        type=str,
+        help="Path to a .json file mapping output category names to integer IDs (e.g., {'cat':0, 'dog':1})"
+    )
+    parser.add_argument(
+        'input_to_output_category_map_file',
+        type=str,
+        help="Path to a .json file mapping input category names to output category names" + \
+            " (e.g., {'old_cat_name':'cat', 'old_dog_name':'dog'})"
+    )
+    parser.add_argument(
+        'output_coco_file',
+        type=str,
+        help='Path to save the remapped COCO .json file'
+    )
+    parser.add_argument(
+        '--allow_unused_categories',
+        action='store_true',
+        help='Allow unmapped categories (by default, errors on unmapped categories)'
+    )
+
+    args = parser.parse_args()
+
+    # Load category mappings
+    with open(args.output_category_map_file, 'r') as f:
+        output_category_name_to_id = json.load(f)
+
+    with open(args.input_to_output_category_map_file, 'r') as f:
+        input_category_name_to_output_category_name = json.load(f)
+
+    # Load COCO data
+    with open(args.input_coco_file, 'r') as f:
+        input_data = json.load(f)
+
+    remap_coco_categories(
+        input_data=input_data,
+        output_category_name_to_id=output_category_name_to_id,
+        input_category_name_to_output_category_name=input_category_name_to_output_category_name,
+        output_file=args.output_coco_file,
+        allow_unused_categories=args.allow_unused_categories
+    )
+
+    print(f'Successfully remapped categories and saved to {args.output_coco_file}')
+
+if __name__ == '__main__':
+    main()

megadetector/data_management/remove_exif.py

@@ -14,6 +14,7 @@ included in package-level dependency lists.  YMMV.
 
 import os
 import glob
+import argparse
 
 from multiprocessing.pool import Pool as Pool
 from tqdm import tqdm
@@ -28,6 +29,12 @@ def remove_exif_from_image(fn):
     pyexiv2 is not thread safe, do not call this function in parallel within a process.
 
     Parallelizing across processes is fine.
+
+    Args:
+        fn (str): image file from which we should remove EXIF information
+
+    Returns:
+        bool: whether EXIF removal succeeded
     """
 
     import pyexiv2 # type: ignore
@@ -40,6 +47,7 @@ def remove_exif_from_image(fn):
         img.close()
     except Exception as e:
         print('EXIF error on {}: {}'.format(fn,str(e)))
+        return False
 
     return True
 
@@ -99,4 +107,45 @@ def remove_exif(image_base_folder,recursive=True,n_processes=1):
 
 #%% Command-line driver
 
-## TODO
+def main():
+    """
+    Command-line interface to remove EXIF data from images.
+    """
+
+    parser = argparse.ArgumentParser(
+        description='Removes EXIF/IPTC/XMP metadata from images in a folder'
+    )
+    parser.add_argument(
+        'image_base_folder',
+        type=str,
+        help='Folder to process for EXIF removal'
+    )
+    parser.add_argument(
+        '--nonrecursive',
+        action='store_true',
+        help="Don't recurse into [image_base_folder] (default is recursive)"
+    )
+    parser.add_argument(
+        '--n_processes',
+        type=int,
+        default=1,
+        help='Number of concurrent processes for EXIF removal (default: 1)'
+    )
+
+    args = parser.parse_args()
+
+    recursive = (not args.nonrecursive)
+
+    print('Processing folder: {}'.format(args.image_base_folder))
+    if not os.path.isdir(args.image_base_folder):
+        raise ValueError('Folder not found at {}'.format(args.image_base_folder))
+
+    remove_exif(
+        image_base_folder=args.image_base_folder,
+        recursive=recursive,
+        n_processes=args.n_processes
+    )
+    print('Finished removing EXIF data')
+
+if __name__ == '__main__':
+    main()

megadetector/data_management/rename_images.py

@@ -32,10 +32,10 @@ def rename_images(input_folder,
     detections into labelme format.
 
     Args:
-        input_folder: the folder to search for images, always recursive
-        output_folder: the folder to which we will copy images; cannot be the
+        input_folder (str): the folder to search for images, always recursive
+        output_folder (str): the folder to which we will copy images; cannot be the
             same as [input_folder]
-        dry_run: only map images, don't actually copy
+        dry_run (bool, optional): only map images, don't actually copy
         verbose (bool, optional): enable additional debug output
         read_exif_options (ReadExifOptions, optional): parameters controlling the reading of
             EXIF information