megadetector 5.0.28__py3-none-any.whl → 5.0.29__py3-none-any.whl

megadetector/postprocessing/load_api_results.py

@@ -18,7 +18,7 @@ Includes functions to read/write the (very very old) .csv results format.
 import json
 import os
 
-from typing import Dict, Mapping, Optional, Tuple
+from typing import Mapping, Optional
 
 import pandas as pd
 
@@ -31,7 +31,7 @@ from megadetector.utils.wi_utils import load_md_or_speciesnet_file
 def load_api_results(api_output_path: str, normalize_paths: bool = True,
                      filename_replacements: Optional[Mapping[str, str]] = None,
                      force_forward_slashes: bool = True
-                     ) -> Tuple[pd.DataFrame, Dict]:
+                     ) -> tuple[pd.DataFrame, dict]:
     r"""
     Loads json-formatted MegaDetector results to a Pandas DataFrame.
 
@@ -48,11 +48,11 @@ def load_api_results(api_output_path: str, normalize_paths: bool = True,
         detection_results: pd.DataFrame, contains at least the columns ['file', 'detections','failure']
         other_fields: a dict containing fields in the results other than 'images'
     """
-    
+
     print('Loading results from {}'.format(api_output_path))
 
     detection_results = load_md_or_speciesnet_file(api_output_path)
-    
+
     # Validate that this is really a detector output file
     for s in ['info', 'detection_categories', 'images']:
         assert s in detection_results, 'Missing field {} in detection results'.format(s)
@@ -65,12 +65,12 @@ def load_api_results(api_output_path: str, normalize_paths: bool = True,
 
     if normalize_paths:
         for image in detection_results['images']:
-            image['file'] = os.path.normpath(image['file'])            
+            image['file'] = os.path.normpath(image['file'])
 
     if force_forward_slashes:
         for image in detection_results['images']:
             image['file'] = image['file'].replace('\\','/')
-            
+
     # Replace some path tokens to match local paths to original blob structure
     if filename_replacements is not None:
         for string_to_replace in filename_replacements.keys():
@@ -79,16 +79,16 @@ def load_api_results(api_output_path: str, normalize_paths: bool = True,
                 im['file'] = im['file'].replace(string_to_replace,replacement_string)
 
     print('Converting results to dataframe')
-    
+
     # If this is a newer file that doesn't include maximum detection confidence values,
     # add them, because our unofficial internal dataframe format includes this.
     for im in detection_results['images']:
         if 'max_detection_conf' not in im:
             im['max_detection_conf'] = ct_utils.get_max_conf(im)
-    
+
     # Pack the json output into a Pandas DataFrame
     detection_results = pd.DataFrame(detection_results['images'])
-    
+
     print('Finished loading MegaDetector results for {} images from {}'.format(
             len(detection_results),api_output_path))
 
@@ -111,7 +111,7 @@ def write_api_results(detection_results_table, other_fields, out_path):
         if 'failure' in im and im['failure'] is None:
             del im['failure']
     fields['images'] = images
-    
+
     # Convert the 'version' field back to a string as per format convention
     try:
         version = other_fields['info']['format_version']
@@ -120,7 +120,7 @@ def write_api_results(detection_results_table, other_fields, out_path):
     except Exception:
         print('Warning: error determining format version')
         pass
-    
+
     # Remove 'max_detection_conf' as per newer file convention (format >= v1.3)
     try:
         version = other_fields['info']['format_version']
@@ -132,20 +132,23 @@ def write_api_results(detection_results_table, other_fields, out_path):
     except Exception:
         print('Warning: error removing max_detection_conf from output')
         pass
-    
+
     with open(out_path, 'w') as f:
         json.dump(fields, f, indent=1)
 
     print('Finished writing detection results to {}'.format(out_path))
 
 
-def load_api_results_csv(filename, normalize_paths=True, filename_replacements={}, nrows=None):
+def load_api_results_csv(filename, normalize_paths=True, filename_replacements=None, nrows=None):
     """
     [DEPRECATED]
-    
+
     Loads .csv-formatted MegaDetector results to a pandas table
     """
 
+    if filename_replacements is None:
+        filename_replacements = {}
+
     print('Loading MegaDetector results from {}'.format(filename))
 
     detection_results = pd.read_csv(filename,nrows=nrows)
@@ -169,12 +172,12 @@ def load_api_results_csv(filename, normalize_paths=True, filename_replacements={
 
         replacement_string = filename_replacements[string_to_replace]
 
-        # iRow = 0
-        for iRow in range(0,len(detection_results)):
-            row = detection_results.iloc[iRow]
+        # i_row = 0
+        for i_row in range(0,len(detection_results)):
+            row = detection_results.iloc[i_row]
             fn = row['image_path']
             fn = fn.replace(string_to_replace,replacement_string)
-            detection_results.at[iRow,'image_path'] = fn
+            detection_results.at[i_row,'image_path'] = fn
 
     print('Finished loading and de-serializing MD results for {} images from {}'.format(
         len(detection_results),filename))
@@ -183,9 +186,9 @@ def load_api_results_csv(filename, normalize_paths=True, filename_replacements={
 
 
 def write_api_results_csv(detection_results, filename):
-    """    
+    """
     [DEPRECATED]
-    
+
     Writes a Pandas table to csv in a way that's compatible with the .csv output
     format.  Currently just a wrapper around to_csv that forces output writing
     to go through a common code path.

megadetector/postprocessing/md_to_coco.py

@@ -3,7 +3,7 @@
 md_to_coco.py
 
 "Converts" MegaDetector output files to COCO format.  "Converts" is in quotes because
-this is an opinionated transformation that requires a confidence threshold for most 
+this is an opinionated transformation that requires a confidence threshold for most
 applications.
 
 Does not currently handle classification information.
@@ -15,6 +15,8 @@ Does not currently handle classification information.
 import os
 import json
 import uuid
+import sys
+import argparse
 
 from tqdm import tqdm
 
@@ -36,40 +38,41 @@ def md_to_coco(md_results_file,
                include_failed_images=True,
                include_annotations_without_bounding_boxes=True,
                empty_category_id='0',
-               overwrite_behavior='skip',               
+               overwrite_behavior='skip',
                verbose=True,
-               image_filename_to_size=None):
+               image_filename_to_size=None,
+               unrecognized_category_handling='error'):
     """
     "Converts" MegaDetector output files to COCO format.  "Converts" is in quotes because
     this is an opinionated transformation that typically requires a confidence threshold.
-    
-    The default confidence threshold is not 0; the assumption is that by default, you are 
+
+    The default confidence threshold is not 0; the assumption is that by default, you are
     going to treat the resulting COCO file as a set of labels.  If you are using the resulting COCO
-    file to *evaluate* a detector, rather than as a set of labels, you likely want a 
-    confidence threshold of 0.  Confidence values will be written to the semi-standard "score" 
+    file to *evaluate* a detector, rather than as a set of labels, you likely want a
+    confidence threshold of 0.  Confidence values will be written to the semi-standard "score"
     field for each image (regardless of the threshold) if preserve_nonstandard_metadata is True.
-    
-    A folder of images is required if width and height information are not available 
+
+    A folder of images is required if width and height information are not available
     in the MD results file.
 
     Args:
-        md_results_file (str): MD results .json file to convert to COCO 
+        md_results_file (str): MD results .json file to convert to COCO
             format
-        coco_output_file (str, optional): COCO .json file to write; if this is None, we'll return 
+        coco_output_file (str, optional): COCO .json file to write; if this is None, we'll return
             a COCO-formatted dict, but won't write it to disk.  If this is 'auto', we'll write to
             [md_results_file_without_extension].coco.json.
         image_folder (str, optional): folder of images, required if 'width' and 'height' are not
             present in the MD results file (they are not required by the format)
         confidence_threshold (float, optional): boxes below this confidence threshold will not be
             included in the output data
-        validate_image_sizes (bool, optional): if this is True, we'll check the image sizes 
+        validate_image_sizes (bool, optional): if this is True, we'll check the image sizes
             regardless of whether "width" and "height" are present in the MD results file.
         info (dict, optional): arbitrary metadata to include in an "info" field in the COCO-formatted
             output
-        preserve_nonstandard_metadata (bool, optional): if this is True, confidence will be preserved in a 
-            non-standard "score" field in each annotation, and any random fields present in each image's 
-            data (e.g. EXIF metadata) will be propagated to COCO output    
-        include_failed_images (bool, optional): if this is True, failed images will be propagated to COCO output 
+        preserve_nonstandard_metadata (bool, optional): if this is True, confidence will be preserved in a
+            non-standard "score" field in each annotation, and any random fields present in each image's
+            data (e.g. EXIF metadata) will be propagated to COCO output
+        include_failed_images (bool, optional): if this is True, failed images will be propagated to COCO output
             with a non-empty "failure" field and no other fields, otherwise failed images will be skipped.
         include_annotations_without_bounding_boxes (bool, optional): if this is True, annotations with
             only class labels (no bounding boxes) will be included in the output.  If this is False, empty
@@ -84,19 +87,26 @@ def md_to_coco(md_results_file,
             image sizes is the slowest step, so if you need to convert many results files at once for the same
             set of images, things will be gobs faster if you read the image sizes in advance and pass them in
             via this argument.  The format used here is the same format output by parallel_get_image_sizes().
-    
+        unrecognized_category_handling (str or float, optional): specifies what to do when encountering category
+            IDs not in the category mapping.  Can be "error", "ignore", or "warning".  Can also be a float,
+            in which case an error is thrown if an unrecognized category has a confidence value higher than
+            this value.
+
     Returns:
         dict: the COCO data dict, identical to what's written to [coco_output_file] if [coco_output_file]
         is not None.
     """
-    
+
     assert isinstance(md_results_file,str)
     assert os.path.isfile(md_results_file), \
         'MD results file {} does not exist'.format(md_results_file)
+    assert (isinstance(unrecognized_category_handling,float)) or \
+           (unrecognized_category_handling in ('error','warning','ignore')), \
+        'Invalid category handling behavior {}'.format(unrecognized_category_handling)
 
     if coco_output_file == 'auto':
         coco_output_file = insert_before_extension(md_results_file,'coco')
-        
+
     if coco_output_file is not None:
         if os.path.isfile(coco_output_file):
             if overwrite_behavior == 'skip':
@@ -120,155 +130,177 @@ def md_to_coco(md_results_file,
                 pass
             elif overwrite_behavior == 'error':
                 raise ValueError('Output file {} exists'.format(coco_output_file))
-            
-    with open(md_results_file,'r') as f:    
-        md_results = json.load(f)    
-        
+
+    with open(md_results_file,'r') as f:
+        md_results = json.load(f)
+
     coco_images = []
     coco_annotations = []
-        
-    print('Converting MD results file {} to COCO file {}...'.format(
-        md_results_file, coco_output_file))
-    
+
+    if verbose:
+        print('Converting MD results file {} to COCO file {}...'.format(
+            md_results_file, coco_output_file))
+
     # im = md_results['images'][0]
     for im in tqdm(md_results['images'],disable=(not verbose)):
-        
+
         coco_im = {}
         coco_im['id'] = im['file']
         coco_im['file_name'] = im['file']
-        
-        # There is no concept of this in the COCO standard        
+
+        # There is no concept of this in the COCO standard
         if 'failure' in im and im['failure'] is not None:
             if include_failed_images:
                 coco_im['failure'] = im['failure']
                 coco_images.append(coco_im)
             continue
-        
+
         # Read/validate image size
         w = None
         h = None
-        
+
         if ('width' not in im) or ('height' not in im) or validate_image_sizes:
             if (image_folder is None) and (image_filename_to_size is None):
-                raise ValueError('Must provide an image folder or a size mapping when height/width need to be read from images')
-                
+                raise ValueError('Must provide an image folder or a size mapping when ' + \
+                                 'height/width need to be read from images')
+
             w = None; h = None
-            
+
             if image_filename_to_size is not None:
-                
+
                 if im['file'] not in image_filename_to_size:
-                    print('Warning: file {} not in image size mapping dict, reading from file'.format(im['file']))
+                    print('Warning: file {} not in image size mapping dict, reading from file'.format(
+                        im['file']))
                 else:
                     image_size = image_filename_to_size[im['file']]
                     if image_size is not None:
                         assert len(image_size) == 2
                         w = image_size[0]
                         h = image_size[1]
-            
+
             if w is None:
-                
+
                 image_file_abs = os.path.join(image_folder,im['file'])
                 pil_im = vis_utils.open_image(image_file_abs)
                 w = pil_im.width
                 h = pil_im.height
-                        
+
             if validate_image_sizes:
                 if 'width' in im:
                     assert im['width'] == w, 'Width mismatch for image {}'.format(im['file'])
                 if 'height' in im:
                     assert im['height'] == h, 'Height mismatch for image {}'.format(im['file'])
         else:
-            
+
             w = im['width']
             h = im['height']
-        
+
         coco_im['width'] = w
         coco_im['height'] = h
-        
+
         # Add other, non-standard fields to the output dict
         if preserve_nonstandard_metadata:
             for k in im.keys():
                 if k not in ('file','detections','width','height'):
                     coco_im[k] = im[k]
-                
+
         coco_images.append(coco_im)
-        
+
         # detection = im['detections'][0]
         for detection in im['detections']:
-            
+
             # Skip below-threshold detections
             if confidence_threshold is not None and detection['conf'] < confidence_threshold:
                 continue
-        
+
             # Create an annotation
-            ann = {}        
+            ann = {}
             ann['id'] = str(uuid.uuid1())
-            ann['image_id'] = coco_im['id']                
-                        
+            ann['image_id'] = coco_im['id']
+
             md_category_id = detection['category']
+
+            if md_category_id not in md_results['detection_categories']:
+
+                s = 'unrecognized category ID {} occurred with confidence {} in file {}'.format(
+                        md_category_id,detection['conf'],im['file'])
+                if isinstance(unrecognized_category_handling,float):
+                    if detection['conf'] > unrecognized_category_handling:
+                        raise ValueError(s)
+                    else:
+                        continue
+                elif unrecognized_category_handling == 'warning':
+                    print('Warning: {}'.format(s))
+                    continue
+                elif unrecognized_category_handling == 'ignore':
+                    continue
+                else:
+                    raise ValueError(s)
+
             coco_category_id = int(md_category_id)
             ann['category_id'] = coco_category_id
-            
+
             if md_category_id != empty_category_id:
-                
+
                 assert 'bbox' in detection,\
                     'Oops: non-empty category with no bbox in {}'.format(im['file'])
-            
+
                 ann['bbox'] = detection['bbox']
-                
+
                 # MegaDetector: [x,y,width,height] (normalized, origin upper-left)
                 # COCO: [x,y,width,height] (absolute, origin upper-left)
                 ann['bbox'][0] = ann['bbox'][0] * coco_im['width']
                 ann['bbox'][1] = ann['bbox'][1] * coco_im['height']
                 ann['bbox'][2] = ann['bbox'][2] * coco_im['width']
-                ann['bbox'][3] = ann['bbox'][3] * coco_im['height']                
-            
+                ann['bbox'][3] = ann['bbox'][3] * coco_im['height']
+
             else:
-            
+
                 # In very esoteric cases, we use the empty category (0) in MD-formatted output files
                 print('Warning: empty category ({}) used for annotation in file {}'.format(
                     empty_category_id,im['file']))
                 pass
-                      
+
             if preserve_nonstandard_metadata:
                 # "Score" is a semi-standard string here, recognized by at least pycocotools
                 # ann['conf'] = detection['conf']
                 ann['score'] = detection['conf']
-        
+
             if 'bbox' in ann or include_annotations_without_bounding_boxes:
-                coco_annotations.append(ann)            
-        
+                coco_annotations.append(ann)
+
         # ...for each detection
-    
+
     # ...for each image
 
     output_dict = {}
-    
+
     if info is not None:
         output_dict['info'] = info
     else:
         output_dict['info'] = {'description':'Converted from MD results file {}'.format(md_results_file)}
     output_dict['info']['confidence_threshold'] = confidence_threshold
-    
+
     output_dict['images'] = coco_images
     output_dict['annotations'] = coco_annotations
-    
+
     output_dict['categories'] = []
-    
+
     for md_category_id in md_results['detection_categories'].keys():
-        
+
         coco_category_id = int(md_category_id)
         coco_category = {'id':coco_category_id,
                          'name':md_results['detection_categories'][md_category_id]}
         output_dict['categories'].append(coco_category)
-        
-    print('Writing COCO output file...')
-    
+
+    if verbose:
+        print('Writing COCO output file...')
+
     if coco_output_file is not None:
         with open(coco_output_file,'w') as f:
             json.dump(output_dict,f,indent=1)
-    
-    return output_dict    
+
+    return output_dict
 
 # ...def md_to_coco(...)
 
@@ -276,11 +308,11 @@ def md_to_coco(md_results_file,
 #%% Interactive driver
 
 if False:
-    
+
     pass
 
     #%% Configure options
-    
+
     md_results_file = os.path.expanduser('~/data/md-test.json')
     coco_output_file = os.path.expanduser('~/data/md-test-coco.json')
     image_folder = os.path.expanduser('~/data/md-test')
@@ -290,10 +322,10 @@ if False:
     info=None
     preserve_nonstandard_metadata=True
     include_failed_images=False
-    
-    
+
+
     #%% Programmatic execution
-    
+
     output_dict = md_to_coco(md_results_file,
                    coco_output_file=coco_output_file,
                    image_folder=image_folder,
@@ -302,10 +334,10 @@ if False:
                    info=info,
                    preserve_nonstandard_metadata=preserve_nonstandard_metadata,
                    include_failed_images=include_failed_images)
-    
-    
+
+
     #%% Command-line example
-        
+
     s = f'python md_to_coco.py {md_results_file} {coco_output_file} {confidence_threshold} '
     if image_folder is not None:
         s += f' --image_folder {image_folder}'
@@ -316,9 +348,9 @@ if False:
 
     print(s); import clipboard; clipboard.copy(s)
 
-    
+
     #%% Preview the resulting file
-    
+
     from megadetector.visualization import visualize_db
     options = visualize_db.DbVizOptions()
     options.parallelize_rendering = True
@@ -327,49 +359,48 @@ if False:
 
     html_file,_ = visualize_db.visualize_db(coco_output_file,
                                               os.path.expanduser('~/tmp/md_to_coco_preview'),
-                                              image_folder,options)    
+                                              image_folder,options)
 
     from megadetector.utils import path_utils # noqa
     path_utils.open_file(html_file)
-    
-    
-#%% Command-line driver
 
-import sys,argparse
 
-def main():
+#%% Command-line driver
+
+def main(): # noqa
 
     parser = argparse.ArgumentParser(
-        description='"Convert" MD output to COCO format, in quotes because this is an opinionated transformation that requires a confidence threshold')
-    
+        description='"Convert" MD output to COCO format, in quotes because this is an opinionated ' + \
+                    'transformation that requires a confidence threshold')
+
     parser.add_argument(
         'md_results_file',
         type=str,
         help='Path to MD results file (.json)')
-    
+
     parser.add_argument(
         'coco_output_file',
         type=str,
         help='Output filename (.json)')
-    
+
     parser.add_argument(
         'confidence_threshold',
         type=float,
         default=default_confidence_threshold,
         help='Confidence threshold (default {})'.format(default_confidence_threshold)
         )
-    
+
     parser.add_argument(
         '--image_folder',
         type=str,
         default=None,
         help='Image folder, only required if we will need to access image sizes'
         )
-    
+
     parser.add_argument(
         '--preserve_nonstandard_metadata',
         action='store_true',
-        help='Preserve metadata that isn\'t normally included in ' + 
+        help='Preserve metadata that isn\'t normally included in ' +
              'COCO-formatted data (e.g. EXIF metadata, confidence values)'
         )
 
@@ -378,7 +409,7 @@ def main():
         action='store_true',
         help='Keep a record of corrupted images in the output; may not be completely COCO-compliant'
         )
-    
+
     if len(sys.argv[1:]) == 0:
         parser.print_help()
         parser.exit()
@@ -392,7 +423,7 @@ def main():
                validate_image_sizes=False,
                info=None,
                preserve_nonstandard_metadata=args.preserve_nonstandard_metadata,
-               include_failed_images=args.include_failed_images)    
-    
+               include_failed_images=args.include_failed_images)
+
 if __name__ == '__main__':
     main()