megadetector 10.0.6__py3-none-any.whl → 10.0.8__py3-none-any.whl

megadetector/data_management/cct_json_utils.py

@@ -305,6 +305,9 @@ class SequenceOptions:
         #: How to handle invalid datetimes: 'error' or 'none'
         self.datetime_conversion_failure_behavior = 'none'
 
+        #: Enable additional debug output
+        self.verbose = False
+
 
 #%% Functions
 
@@ -331,7 +334,9 @@ def write_object_with_serialized_datetimes(d,json_fn):
         json.dump(d,f,indent=1,default=json_serialize_datetime)
 
 
-def parse_datetimes_from_cct_image_list(images,conversion_failure_behavior='error'):
+def parse_datetimes_from_cct_image_list(images,
+                                        conversion_failure_behavior='error',
+                                        verbose=False):
     """
     Given the "images" field from a COCO camera traps dictionary, converts all
     string-formatted datetime fields to Python datetimes, making reasonable assumptions
@@ -342,6 +347,7 @@ def parse_datetimes_from_cct_image_list(images,conversion_failure_behavior='erro
         conversion_failure_behavior (str, optional): determines what happens on a failed
             conversion; can be "error" (raise an error), "str" (leave as a string), or
             "none" (convert to None)
+        verbose (bool, optional): enable additional debug output
 
     Returns:
         images: the input list, with datetimes converted (after modifying in place)
@@ -359,14 +365,17 @@ def parse_datetimes_from_cct_image_list(images,conversion_failure_behavior='erro
             dt = dateutil.parser.parse(im['datetime'])
             im['datetime'] = dt
         except Exception as e:
-            s = 'could not parse datetime {}: {}'.format(str(im['datetime']),str(e))
+            s = 'could not parse datetime {} from {}: {}'.format(
+                str(im['datetime']),im['file_name'],str(e))
             if conversion_failure_behavior == 'error':
                 raise ValueError(s)
             elif conversion_failure_behavior == 'str':
-                print('Warning: {}'.format(s))
+                if verbose:
+                    print('Warning: {}'.format(s))
                 pass
             elif conversion_failure_behavior == 'none':
-                print('Warning: {}'.format(s))
+                if verbose:
+                    print('Warning: {}'.format(s))
                 im['datetime'] = None
 
     # ...for each image
@@ -450,7 +459,8 @@ def create_sequences(image_info,options=None):
 
     # Modifies the images in place
     _ = parse_datetimes_from_cct_image_list(image_info,
-            conversion_failure_behavior=options.datetime_conversion_failure_behavior)
+            conversion_failure_behavior=options.datetime_conversion_failure_behavior,
+            verbose=options.verbose)
 
     n_invalid_datetimes = 0
     for im in image_info:
@@ -505,7 +515,7 @@ def create_sequences(image_info,options=None):
                 delta = (im['datetime'] - previous_datetime).total_seconds()
 
             # Start a new sequence if necessary, including the case where this datetime is invalid
-            if delta is None or delta > options.episode_interval_seconds or invalid_datetime:
+            if (delta is None) or (delta > options.episode_interval_seconds) or (invalid_datetime):
                 next_frame_number = 0
                 current_sequence_id = 'location_{}_sequence_index_{}'.format(
                     location,str(next_sequence_number).zfill(5))

megadetector/data_management/databases/subset_json_db.py

@@ -18,13 +18,20 @@ import json
 import argparse
 
 from tqdm import tqdm
-from megadetector.utils import ct_utils
 from copy import copy
 
+from megadetector.utils import ct_utils
+from megadetector.utils.ct_utils import sort_list_of_dicts_by_key
+
 
 #%% Functions
 
-def subset_json_db(input_json, query, output_json=None, ignore_case=False, verbose=False):
+def subset_json_db(input_json,
+                   query,
+                   output_json=None,
+                   ignore_case=False,
+                   remap_categories=True,
+                   verbose=False):
     """
     Given a json file (or dictionary already loaded from a json file), produce a new
     database containing only the images whose filenames contain the string 'query',
@@ -36,6 +43,8 @@ def subset_json_db(input_json, query, output_json=None, ignore_case=False, verbo
             contain this string.  If this is a list, test for exact matches.
         output_json (str, optional): file to write the resulting .json file to
         ignore_case (bool, optional): whether to perform a case-insensitive search for [query]
+        remap_categories (bool, optional): trim the category list to only the categores used
+            in the subset
         verbose (bool, optional): enable additional debug output
 
     Returns:
@@ -92,6 +101,52 @@ def subset_json_db(input_json, query, output_json=None, ignore_case=False, verbo
     output_data['images'] = images
     output_data['annotations'] = annotations
 
+    # Remap categories if necessary
+    if remap_categories:
+
+        category_ids_used = set()
+        for ann in annotations:
+            category_ids_used.add(ann['category_id'])
+
+        if verbose:
+            print('Keeping {} of {} categories'.format(
+                len(category_ids_used),len(input_data['categories'])))
+
+        input_category_id_to_output_category_id = {}
+
+        next_category_id = 0
+
+        # Build mappings from old to new category IDs
+        for input_category_id in category_ids_used:
+            assert isinstance(input_category_id,int), \
+                'Illegal category ID {}'.format(input_category_id)
+            output_category_id = next_category_id
+            next_category_id = next_category_id + 1
+            input_category_id_to_output_category_id[input_category_id] = output_category_id
+
+        # Modify the annotations
+        for ann in annotations:
+            assert ann['category_id'] in input_category_id_to_output_category_id
+            ann['category_id'] = input_category_id_to_output_category_id[ann['category_id']]
+
+        output_categories = []
+
+        # Re-write the category table
+        for cat in input_data['categories']:
+
+            if cat['id'] in input_category_id_to_output_category_id:
+
+                # There may be non-required fields, so don't just create an empty dict
+                # and copy the name/id field, keep the original dict other than "id"
+                output_category = copy(cat)
+                output_category['id'] = input_category_id_to_output_category_id[cat['id']]
+                output_categories.append(output_category)
+
+        output_categories = sort_list_of_dicts_by_key(output_categories,'id')
+        output_data['categories'] = output_categories
+
+    # ...if we need to remap categories
+
     # Write the output file if requested
     if output_json is not None:
         if verbose:

megadetector/detection/pytorch_detector.py

@@ -328,7 +328,8 @@ def _initialize_yolo_imports(model_type='yolov5',
     if try_yolov5_import and not utils_imported:
 
         try:
-            from yolov5.utils.general import non_max_suppression, xyxy2xywh # noqa
+            # from yolov5.utils.general import non_max_suppression # type: ignore
+            from yolov5.utils.general import xyxy2xywh # noqa
             from yolov5.utils.augmentations import letterbox # noqa
             try:
                 from yolov5.utils.general import scale_boxes as scale_coords
@@ -348,7 +349,8 @@ def _initialize_yolo_imports(model_type='yolov5',
 
         try:
 
-            from yolov9.utils.general import non_max_suppression, xyxy2xywh # noqa
+            # from yolov9.utils.general import non_max_suppression # noqa
+            from yolov9.utils.general import xyxy2xywh # noqa
             from yolov9.utils.augmentations import letterbox # noqa
             from yolov9.utils.general import scale_boxes as scale_coords # noqa
             utils_imported = True
@@ -378,7 +380,12 @@ def _initialize_yolo_imports(model_type='yolov5',
 
         try:
 
-            from ultralytics.utils.ops import non_max_suppression # type: ignore # noqa
+            # The non_max_suppression() function moved from the ops module to the nms module
+            # in mid-2025
+            try:
+                from ultralytics.utils.ops import non_max_suppression # type: ignore # noqa
+            except Exception:
+                from ultralytics.utils.nms import non_max_suppression # type: ignore # noqa
             from ultralytics.utils.ops import xyxy2xywh # type: ignore # noqa
 
             # In the ultralytics package, scale_boxes and scale_coords both exist;
@@ -444,9 +451,9 @@ def _initialize_yolo_imports(model_type='yolov5',
             if verbose:
                 print('Imported utils from ultralytics package')
 
-        except Exception:
+        except Exception as e:
 
-            # print('Ultralytics module import failed')
+            print('Ultralytics module import failed: {}'.format(str(e)))
             pass
 
     # If we haven't succeeded yet, assume the YOLOv5 repo is on our PYTHONPATH.
@@ -455,7 +462,8 @@ def _initialize_yolo_imports(model_type='yolov5',
         try:
 
             # import pre- and post-processing functions from the YOLOv5 repo
-            from utils.general import non_max_suppression, xyxy2xywh # type: ignore
+            # from utils.general import non_max_suppression # type: ignore
+            from utils.general import xyxy2xywh # type: ignore
             from utils.augmentations import letterbox # type: ignore
 
             # scale_coords() is scale_boxes() in some YOLOv5 versions
@@ -1283,17 +1291,23 @@ class PTDetector:
         else:
             nms_iou_thres = 0.6
 
-        pred = nms(prediction=pred,
-                   conf_thres=detection_threshold,
-                   iou_thres=nms_iou_thres)
+        use_library_nms = False
+
+        # Model output format changed in recent ultralytics packages, and the nms implementation
+        # in this module hasn't been updated to handle that format yet.
+        if (yolo_model_type_imported is not None) and (yolo_model_type_imported == 'ultralytics'):
+            use_library_nms = True
 
-        # For posterity, the ultralytics implementation
-        if False:
+        if use_library_nms:
             pred = non_max_suppression(prediction=pred,
-                                       conf_thres=detection_threshold,
-                                       iou_thres=nms_iou_thres,
-                                       agnostic=False,
-                                       multi_label=False)
+                                    conf_thres=detection_threshold,
+                                    iou_thres=nms_iou_thres,
+                                    agnostic=False,
+                                    multi_label=False)
+        else:
+            pred = nms(prediction=pred,
+                    conf_thres=detection_threshold,
+                    iou_thres=nms_iou_thres)
 
         assert isinstance(pred, list)
         assert len(pred) == len(batch_metadata), \

megadetector/detection/run_inference_with_yolov5_val.py

@@ -159,7 +159,9 @@ class YoloInferenceOptions:
         #: These are deliberately offset from the standard MD categories; YOLOv5
         #: needs categories IDs to start at 0.
         #:
-        #: This can also be a string that points to a YOLO dataset.yaml file.
+        #: This can also be a string that points to any class mapping file supported
+        #: by read_classes_from_yolo_dataset_file(): a YOLO dataset.yaml file, a text
+        #: file with a list of classes, or a .json file with an ID --> name dict
         self.yolo_category_id_to_name = {0:'animal',1:'person',2:'vehicle'}
 
         #: What should we do if the output file already exists?

megadetector/detection/run_tiled_inference.py

@@ -907,7 +907,10 @@ if False:
 
 #%% Command-line driver
 
-def main(): # noqa
+def main():
+    """
+    Command-line driver for run_tiled_inference
+    """
 
     parser = argparse.ArgumentParser(
         description='Chop a folder of images up into tiles, run MD on the tiles, and stitch the results together')
@@ -956,7 +959,7 @@ def main(): # noqa
         '--detector_options',
         type=str,
         default=None,
-        help=('A list of detector options (key-value pairs) to '))
+        help=('A list of detector options (key-value pairs)'))
 
     # detector_options = parse_kvp_list(args.detector_options)
 

megadetector/detection/video_utils.py

@@ -22,6 +22,7 @@ from functools import partial
 from inspect import signature
 
 from megadetector.utils import path_utils
+from megadetector.utils.path_utils import clean_path
 from megadetector.utils.ct_utils import sort_list_of_dicts_by_key
 from megadetector.visualization import visualization_utils as vis_utils
 
@@ -592,7 +593,7 @@ def video_to_frames(input_video_file,
                     quality=None,
                     max_width=None,
                     frames_to_extract=None,
-                    allow_empty_videos=False):
+                    allow_empty_videos=True):
     """
     Renders frames from [input_video_file] to .jpg files in [output_folder].
 
@@ -618,8 +619,8 @@ def video_to_frames(input_video_file,
             a single frame number.  In the special case where frames_to_extract
             is [], this function still reads video frame rates and verifies that videos
             are readable, but no frames are extracted.
-        allow_empty_videos (bool, optional): Just print a warning if a video appears to have no
-            frames (by default, this is an error).
+        allow_empty_videos (bool, optional): Just print a warning if a video appears to have
+            no frames (by default, this is an error).
 
     Returns:
         tuple: length-2 tuple containing (list of frame filenames,frame rate)
@@ -883,7 +884,14 @@ def _video_to_frames_for_folder(relative_fn,input_folder,output_folder_base,
 
     # Create the target output folder
     output_folder_video = os.path.join(output_folder_base,relative_fn)
-    os.makedirs(output_folder_video,exist_ok=True)
+    try:
+        os.makedirs(output_folder_video,exist_ok=True)
+    except Exception:
+        output_folder_clean = clean_path(output_folder_video)
+        print('Warning: failed to create folder {}, trying {}'.format(
+            output_folder_video,output_folder_clean))
+        output_folder_video = output_folder_clean
+        os.makedirs(output_folder_video,exist_ok=True)
 
     # Render frames
     # input_video_file = input_fn_absolute; output_folder = output_folder_video
@@ -1090,6 +1098,9 @@ class FrameToVideoOptions:
         #: Are frame rates required?
         self.frame_rates_are_required = False
 
+        #: Enable additional debug output
+        self.verbose = False
+
 
 def frame_results_to_video_results(input_file,
                                    output_file,
@@ -1176,9 +1187,14 @@ def frame_results_to_video_results(input_file,
 
         if (video_filename_to_frame_rate is not None):
 
-            if options.frame_rates_are_required:
-                assert video_name in video_filename_to_frame_rate, \
-                    'Could not determine frame rate for {}'.format(video_name)
+            if video_name not in video_filename_to_frame_rate:
+
+                s = 'Could not determine frame rate for {}'.format(video_name)
+                if options.frame_rates_are_required:
+                    raise ValueError(s)
+                elif options.verbose:
+                    print('Warning: {}'.format(s))
+
             if video_name in video_filename_to_frame_rate:
                 im_out['frame_rate'] = video_filename_to_frame_rate[video_name]