PyPI - megadetector - Versions diffs - 5.0.7__py3-none-any.whl → 5.0.8__py3-none-any.whl - Mend

megadetector 5.0.7py3-none-any.whl → 5.0.8py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of megadetector might be problematic. Click here for more details.

Files changed (48) hide show

api/batch_processing/data_preparation/manage_local_batch.py +28 -14
api/batch_processing/postprocessing/combine_api_outputs.py +2 -2
api/batch_processing/postprocessing/compare_batch_results.py +1 -1
api/batch_processing/postprocessing/convert_output_format.py +24 -6
api/batch_processing/postprocessing/load_api_results.py +1 -3
api/batch_processing/postprocessing/md_to_labelme.py +118 -51
api/batch_processing/postprocessing/merge_detections.py +30 -5
api/batch_processing/postprocessing/postprocess_batch_results.py +24 -12
api/batch_processing/postprocessing/remap_detection_categories.py +163 -0
api/batch_processing/postprocessing/render_detection_confusion_matrix.py +15 -12
api/batch_processing/postprocessing/repeat_detection_elimination/repeat_detections_core.py +2 -2
data_management/cct_json_utils.py +7 -2
data_management/coco_to_labelme.py +263 -0
data_management/coco_to_yolo.py +7 -4
data_management/databases/integrity_check_json_db.py +68 -59
data_management/databases/subset_json_db.py +1 -1
data_management/get_image_sizes.py +44 -26
data_management/importers/animl_results_to_md_results.py +1 -3
data_management/importers/noaa_seals_2019.py +1 -1
data_management/labelme_to_coco.py +252 -143
data_management/labelme_to_yolo.py +95 -52
data_management/lila/create_lila_blank_set.py +106 -23
data_management/lila/download_lila_subset.py +133 -65
data_management/lila/generate_lila_per_image_labels.py +1 -1
data_management/lila/lila_common.py +8 -38
data_management/read_exif.py +65 -16
data_management/remap_coco_categories.py +84 -0
data_management/resize_coco_dataset.py +3 -22
data_management/wi_download_csv_to_coco.py +239 -0
data_management/yolo_to_coco.py +283 -83
detection/run_detector_batch.py +12 -3
detection/run_inference_with_yolov5_val.py +10 -3
detection/run_tiled_inference.py +2 -2
detection/tf_detector.py +2 -1
detection/video_utils.py +1 -1
md_utils/ct_utils.py +22 -3
md_utils/md_tests.py +11 -2
md_utils/path_utils.py +206 -32
md_utils/url_utils.py +66 -1
md_utils/write_html_image_list.py +12 -3
md_visualization/visualization_utils.py +363 -72
md_visualization/visualize_db.py +33 -10
{megadetector-5.0.7.dist-info → megadetector-5.0.8.dist-info}/METADATA +10 -12
{megadetector-5.0.7.dist-info → megadetector-5.0.8.dist-info}/RECORD +47 -44
{megadetector-5.0.7.dist-info → megadetector-5.0.8.dist-info}/WHEEL +1 -1
md_visualization/visualize_megadb.py +0 -183
{megadetector-5.0.7.dist-info → megadetector-5.0.8.dist-info}/LICENSE +0 -0
{megadetector-5.0.7.dist-info → megadetector-5.0.8.dist-info}/top_level.txt +0 -0

api/batch_processing/postprocessing/postprocess_batch_results.py CHANGED Viewed

@@ -27,7 +27,6 @@ import os
 import sys
 import time
 import uuid
-import urllib
 import warnings
 import random
@@ -53,7 +52,6 @@ from md_utils import path_utils
 from data_management.cct_json_utils import (CameraTrapJsonUtils, IndexedJsonDb)
 from api.batch_processing.postprocessing.load_api_results import load_api_results
 from md_utils.ct_utils import args_to_object
-from md_utils.ct_utils import invert_dictionary
 from detection.run_detector import get_typical_confidence_threshold_from_results
@@ -484,7 +482,14 @@ def render_bounding_boxes(
     # Optionally add links back to the original images
     if options.link_images_to_originals and (image_full_path is not None):
-        info['linkTarget'] = urllib.parse.quote(image_full_path)
+        # Handling special characters in links has been pushed down into
+        # write_html_image_list
+        #
+        # link_target = image_full_path.replace('\\','/')
+        # link_target  = urllib.parse.quote(link_target)
+        link_target = image_full_path
+        info['linkTarget'] = link_target
     return info
@@ -848,7 +853,7 @@ def process_batch_results(options: PostProcessingOptions
     ground_truth_indexed_db = None
     if (options.ground_truth_json_file is not None):
-        assert (options.confidence_threshold is None) or (isinstance(confidence_threshold,float)), \
+        assert (options.confidence_threshold is None) or (isinstance(options.confidence_threshold,float)), \
             'Variable confidence thresholds are not supported when supplying ground truth'
     if (options.ground_truth_json_file is not None) and (len(options.ground_truth_json_file) > 0):
@@ -876,7 +881,7 @@ def process_batch_results(options: PostProcessingOptions
     # If the caller hasn't supplied results, load them
     if options.api_detection_results is None:
         detections_df, other_fields = load_api_results(
-            options.api_output_file, normalize_paths=True,
+            options.api_output_file, force_forward_slashes=True,
             filename_replacements=options.api_output_filename_replacements)
         ppresults.api_detection_results = detections_df
         ppresults.api_other_fields = other_fields
@@ -1087,7 +1092,7 @@ def process_batch_results(options: PostProcessingOptions
             (precision_at_confidence_threshold + recall_at_confidence_threshold)
         print('At a confidence threshold of {:.1%}, precision={:.1%}, recall={:.1%}, f1={:.1%}'.format(
-                str(options.confidence_threshold), precision_at_confidence_threshold,
+                options.confidence_threshold, precision_at_confidence_threshold,
                 recall_at_confidence_threshold, f1))
         ##%% Collect classification results, if they exist
@@ -1289,7 +1294,8 @@ def process_batch_results(options: PostProcessingOptions
             for file_info in tqdm(files_to_render):
                 rendering_results.append(render_image_with_gt(
                     file_info,ground_truth_indexed_db,
-                    detection_categories,classification_categories))
+                    detection_categories,classification_categories,
+                    options=options))
         elapsed = time.time() - start_time
         # Map all the rendering results in the list rendering_results into the
@@ -1319,6 +1325,12 @@ def process_batch_results(options: PostProcessingOptions
             image_counts['tp']
         )
+        confidence_threshold_string = ''
+        if isinstance(options.confidence_threshold,float):
+            confidence_threshold_string = '{:.2%}'.format(options.confidence_threshold)
+        else:
+            confidence_threshold_string = str(options.confidence_threshold)
         index_page = """<html>
         {}
         <body>
@@ -1333,7 +1345,7 @@ def process_batch_results(options: PostProcessingOptions
         <h3>Sample images</h3>
         <div class="contentdiv">
-        <p>A sample of {} images, annotated with detections above {:.1%} confidence.</p>
+        <p>A sample of {} images, annotated with detections above confidence {}.</p>
         <a href="tp.html">True positives (TP)</a> ({}) ({:0.1%})<br/>
         CLASSIFICATION_PLACEHOLDER_1
         <a href="tn.html">True negatives (TN)</a> ({}) ({:0.1%})<br/>
@@ -1343,7 +1355,7 @@ def process_batch_results(options: PostProcessingOptions
         </div>
         """.format(
             style_header,job_name_string,model_version_string,
-            image_count, str(options.confidence_threshold),
+            image_count, confidence_threshold_string,
             all_tp_count, all_tp_count/total_count,
             image_counts['tn'], image_counts['tn']/total_count,
             image_counts['fp'], image_counts['fp']/total_count,
@@ -1353,11 +1365,11 @@ def process_batch_results(options: PostProcessingOptions
         index_page += """
             <h3>Detection results</h3>
             <div class="contentdiv">
-            <p>At a confidence threshold of {:0.1%}, precision={:0.1%}, recall={:0.1%}</p>
+            <p>At a confidence threshold of {}, precision={:0.1%}, recall={:0.1%}</p>
             <p><strong>Precision/recall summary for all {} images</strong></p><img src="{}"><br/>
             </div>
             """.format(
-                str(options.confidence_threshold), precision_at_confidence_threshold, recall_at_confidence_threshold,
+                confidence_threshold_string, precision_at_confidence_threshold, recall_at_confidence_threshold,
                 len(detections_df), pr_figure_relative_filename
            )
@@ -1589,7 +1601,7 @@ def process_batch_results(options: PostProcessingOptions
         confidence_threshold_string = ''
         if isinstance(options.confidence_threshold,float):
-            confidence_threshold_string = '{:.1%}'.format(options.confidence_threshold)
+            confidence_threshold_string = '{:.2%}'.format(options.confidence_threshold)
         else:
             confidence_threshold_string = str(options.confidence_threshold)

api/batch_processing/postprocessing/remap_detection_categories.py ADDED Viewed

@@ -0,0 +1,163 @@
+########
+#
+# remap_detection_categories.py
+#
+# Given a MegaDetector results file, remap the category IDs according to a specified
+# dictionary, writing the results to a new file.
+#
+# Currently only supports remapping detection categories, not classification categories.
+#
+########
+#%% Constants and imports
+import json
+import os
+from tqdm import tqdm
+from md_utils.ct_utils import invert_dictionary
+#%% Main function
+def remap_detection_categories(input_file,
+                               output_file,
+                               target_category_map,
+                               extra_category_handling='error',
+                               overwrite=False):
+    """
+    Given a MD results file [input_file], remap the category IDs according to the dictionary
+    [target_category_map], writing the results to [output_file].  The remapped dictionary needs to have
+    the same category names as the input file's detection_categories dictionary.
+    Currently only supports remapping detection categories, not classification categories.
+    target_category_map can also be a MD results file, in which case we'll use that file's
+    detection_categories dictionary.
+    [extra_category_handling] specifies what we should do if categories are present in the source file
+    that are not present in the target mapping.
+    'error' == Error in this case.
+    'drop_if_unused' == Don't include these in the output file's category mappings if they are unused,
+       error if they are.
+    'remap' == Remap to unused category IDs.  This is reserved for future use, not currently implemented.
+    """
+    if os.path.exists(output_file) and (not overwrite):
+        print('File {} exists, bypassing remapping'.format(output_file))
+        return
+    assert os.path.isfile(input_file), \
+        'File {} does not exist'.format(input_file)
+    # If "target_category_map" is passed as a filename, load the "detection_categories"
+    # dict.
+    if isinstance(target_category_map,str):
+        target_categories_file = target_category_map
+        with open(target_categories_file,'r') as f:
+            d = json.load(f)
+            target_category_map = d['detection_categories']
+    assert isinstance(target_category_map,dict)
+    with open(input_file,'r') as f:
+        input_data = json.load(f)
+    input_images = input_data['images']
+    input_categories = input_data['detection_categories']
+    # Figure out which categories are actually used
+    used_category_ids = set()
+    for im in input_images:
+        if 'detections' not in im or im['detections'] is None:
+            continue
+        for det in im['detections']:
+            used_category_ids.add(det['category'])
+    used_category_names = [input_categories[cid] for cid in used_category_ids]
+    input_names_set = set(input_categories.values())
+    output_names_set = set(target_category_map.values())
+    # category_name = list(input_names_set)[0]
+    for category_name in input_names_set:
+        if category_name in output_names_set:
+            continue
+        if extra_category_handling == 'error':
+            raise ValueError('Category {} present in source but not in target'.format(category_name))
+        elif extra_category_handling == 'drop_if_unused':
+            if category_name in used_category_names:
+                raise ValueError('Category {} present (and used) in source but not in target'.format(
+                    category_name))
+            else:
+                print('Category {} is unused and not present in the target mapping, ignoring'.format(
+                    category_name))
+                continue
+        elif extra_category_handling == 'remap':
+            raise NotImplementedError('Remapping of extra category IDs not yet implemented')
+        else:
+            raise ValueError('Unrecognized extra category handling scheme {}'.format(
+                extra_category_handling))
+    output_category_name_to_output_category_id = invert_dictionary(target_category_map)
+    input_category_id_to_output_category_id = {}
+    for input_category_id in input_categories.keys():
+        category_name = input_categories[input_category_id]
+        if category_name not in output_category_name_to_output_category_id:
+            assert category_name not in used_category_names
+        else:
+            output_category_id = output_category_name_to_output_category_id[category_name]
+            input_category_id_to_output_category_id[input_category_id] = output_category_id
+    # im = input_images[0]
+    for im in tqdm(input_images):
+        if 'detections' not in im or im['detections'] is None:
+            continue
+        # det = im['detections'][0]
+        for det in im['detections']:
+            det['category'] = input_category_id_to_output_category_id[det['category']]
+    input_data['detection_categories'] = target_category_map
+    with open(output_file,'w') as f:
+        json.dump(input_data,f,indent=1)
+    print('Saved remapped results to {}'.format(output_file))
+#%% Interactive driver
+if False:
+    pass
+    #%%
+    target_categories_file = '/home/dmorris/tmp/usgs-tegus/model-comparison/all-classes_usgs-only_yolov5x6.json'
+    target_category_map = target_categories_file
+    input_file = '/home/dmorris/tmp/usgs-tegus/model-comparison/all-classes_usgs-goannas-lilablanks_yolov5x6-20240223.json'
+    output_file = input_file.replace('.json','_remapped.json')
+    assert output_file != input_file
+    overwrite = True
+    extra_category_handling = 'drop_if_unused'
+    remap_detection_categories(input_file=input_file,
+                               output_file=output_file,
+                               target_category_map=target_category_map,
+                               extra_category_handling=extra_category_handling,
+                               overwrite=overwrite)
+#%% Command-line driver
+# TODO

api/batch_processing/postprocessing/render_detection_confusion_matrix.py CHANGED Viewed

@@ -56,13 +56,13 @@ def render_image(im,render_image_constants):
     assert im['file'] in filename_to_ground_truth_im
-    input_file = os.path.join(image_folder,im['file'])
-    assert os.path.isfile(input_file)
     output_file = image_to_output_file(im,preview_images_folder)
     if os.path.isfile(output_file) and not force_render_images:
         return output_file
+    input_file = os.path.join(image_folder,im['file'])
+    assert os.path.isfile(input_file)
     detections_to_render = []
     for det in im['detections']:
@@ -82,8 +82,12 @@ def render_image(im,render_image_constants):
 #%% Main function
-def render_detection_confusion_matrix(ground_truth_file,results_file,image_folder,preview_folder,
-                                      force_render_images=False, confidence_thresholds=None,
+def render_detection_confusion_matrix(ground_truth_file,
+                                      results_file,
+                                      image_folder,
+                                      preview_folder,
+                                      force_render_images=False,
+                                      confidence_thresholds=None,
                                       rendering_confidence_thresholds=None,
                                       target_image_size=(1280,-1),
                                       parallelize_rendering=True,
@@ -223,7 +227,7 @@ def render_detection_confusion_matrix(ground_truth_file,results_file,image_folde
     filename_to_predicted_categories = defaultdict(set)
     predicted_category_name_to_filenames = defaultdict(set)
-    # im = md_results['images'][0]
+    # im = md_formatted_results['images'][0]
     for im in tqdm(md_formatted_results['images']):
         assert im['file'] in filename_to_ground_truth_im
@@ -247,9 +251,6 @@ def render_detection_confusion_matrix(ground_truth_file,results_file,image_folde
     category_name_to_image_lists = {}
-    # These may not be identical; currently the ground truth contains an "unknown" category
-    # results_category_names = sorted(list(results_category_id_to_name.values()))
     sub_page_tokens = ['fn','tn','fp','tp']
     for category_name in ground_truth_category_names:
@@ -296,7 +297,7 @@ def render_detection_confusion_matrix(ground_truth_file,results_file,image_folde
                         assignment = 'tn'
             category_name_to_image_lists[category_name][assignment].append(filename)
     # ...for each filename
@@ -333,8 +334,8 @@ def render_detection_confusion_matrix(ground_truth_file,results_file,image_folde
             results_category_name_to_confidence = defaultdict(int)
             for det in results_im['detections']:
                 category_name = results_category_id_to_name[det['category']]
-                detection_threshold = rendering_confidence_thresholds['default']
-                if category_name in rendering_confidence_thresholds:
+                detection_threshold = confidence_thresholds['default']
+                if category_name in confidence_thresholds:
                     detection_threshold = confidence_thresholds[category_name]
                 if det['conf'] > detection_threshold:
                     results_category_name_to_confidence[category_name] = max(
@@ -354,6 +355,8 @@ def render_detection_confusion_matrix(ground_truth_file,results_file,image_folde
         confusion_matrix[ground_truth_category_index,predicted_category_index] += 1
+    # ...for each file
     plt.ioff()
     fig_h = 3 + 0.3 * n_categories

api/batch_processing/postprocessing/repeat_detection_elimination/repeat_detections_core.py CHANGED Viewed

@@ -181,7 +181,7 @@ class RepeatDetectionOptions:
     # Optionally show a grid that includes a sample image for the detection, plus
     # the top N additional detections
-    bRenderDetectionTiles = False
+    bRenderDetectionTiles = True
     # If this is None, we'll render at the width of the original image
     detectionTilesPrimaryImageWidth = None
@@ -193,7 +193,7 @@ class RepeatDetectionOptions:
     # of luck.
     detectionTilesCroppedGridWidth = 0.6
     detectionTilesPrimaryImageLocation='right'
-    detectionTilesMaxCrops = None
+    detectionTilesMaxCrops = 250
     # If bRenderOtherDetections is True, what color should we use to render the
     # (hopefully pretty subtle) non-target detections?

data_management/cct_json_utils.py CHANGED Viewed

@@ -142,7 +142,8 @@ class IndexedJsonDb:
     def __init__(self, json_filename: Union[str, JSONObject],
                  b_normalize_paths: bool = False,
                  filename_replacements: Optional[Mapping[str, str]] = None,
-                 b_convert_classes_to_lower: bool = True):
+                 b_convert_classes_to_lower: bool = True,
+                 b_force_forward_slashes: bool = True):
         """
         json_filename can also be an existing json db
         """
@@ -162,11 +163,15 @@ class IndexedJsonDb:
             for c in self.db['categories']:
                 c['name'] = c['name'].lower()
+        # Normalize paths to simplify comparisons later
         if b_normalize_paths:
-            # Normalize paths to simplify comparisons later
             for im in self.db['images']:
                 im['file_name'] = os.path.normpath(im['file_name'])
+        if b_force_forward_slashes:
+            for im in self.db['images']:
+                im['file_name'] = im['file_name'].replace('\\','/')
         if filename_replacements is not None:
             for s in filename_replacements:
                 # Make custom replacements in filenames, typically used to

data_management/coco_to_labelme.py ADDED Viewed

@@ -0,0 +1,263 @@
+########
+#
+# coco_to_labelme.py
+#
+# Converts a COCO dataset to labelme format (one .json per image file).
+#
+# If you want to convert YOLO data to labelme, use yolo_to_coco, then coco_to_labelme.
+#
+########
+#%% Imports and constants
+import os
+import json
+from tqdm import tqdm
+from collections import defaultdict
+from md_visualization.visualization_utils import open_image
+#%% Functions
+def get_labelme_dict_for_image_from_coco_record(im,annotations,categories,info=None):
+    """
+    For the given image struct in COCO format and associated list of annotations, reformat the detections
+    into labelme format.  Returns a dict.  All annotations in this list should point to this image.
+    "categories" is in the standard COCO format.
+    'height' and 'width' are required in [im].
+    """
+    image_base_name = os.path.basename(im['file_name'])
+    output_dict = {}
+    if info is not None:
+        output_dict['custom_info'] = info
+    output_dict['version'] = '5.3.0a0'
+    output_dict['flags'] = {}
+    output_dict['shapes'] = []
+    output_dict['imagePath'] = image_base_name
+    output_dict['imageHeight'] = im['height']
+    output_dict['imageWidth'] = im['width']
+    output_dict['imageData'] = None
+    # Store COCO categories in case we want to reconstruct the original IDs later
+    output_dict['coco_categories'] = categories
+    category_id_to_name = {c['id']:c['name'] for c in categories}
+    if 'flags' in im:
+        output_dict['flags'] = im['flags']
+    # ann = annotations[0]
+    for ann in annotations:
+        if 'bbox' not in ann:
+            continue
+        shape = {}
+        shape['label'] = category_id_to_name[ann['category_id']]
+        shape['shape_type'] = 'rectangle'
+        shape['description'] = ''
+        shape['group_id'] = None
+        # COCO boxes are [x_min, y_min, width_of_box, height_of_box] (absolute)
+        #
+        # labelme boxes are [[x0,y0],[x1,y1]] (absolute)
+        x0 = ann['bbox'][0]
+        y0 = ann['bbox'][1]
+        x1 = ann['bbox'][0] + ann['bbox'][2]
+        y1 = ann['bbox'][1] + ann['bbox'][3]
+        shape['points'] = [[x0,y0],[x1,y1]]
+        output_dict['shapes'].append(shape)
+    # ...for each detection
+    return output_dict
+# ...def get_labelme_dict_for_image()
+def coco_to_labelme(coco_data,image_base,overwrite=False,bypass_image_size_check=False,verbose=False):
+    """
+    For all the images in [coco_data] (a dict or a filename), write a .json file in
+    labelme format alongside the corresponding relative path within image_base.
+    """
+    # Load COCO data if necessary
+    if isinstance(coco_data,str):
+        with open(coco_data,'r') as f:
+            coco_data = json.load(f)
+    assert isinstance(coco_data,dict)
+    ## Read image sizes if necessary
+    if bypass_image_size_check:
+        print('Bypassing size check')
+    else:
+        # TODO: parallelize this loop
+        print('Reading/validating image sizes...')
+        # im = coco_data['images'][0]
+        for im in tqdm(coco_data['images']):
+            # Make sure this file exists
+            im_full_path = os.path.join(image_base,im['file_name'])
+            assert os.path.isfile(im_full_path), 'Image file {} does not exist'.format(im_full_path)
+            # Load w/h information if necessary
+            if 'height' not in im or 'width' not in im:
+                try:
+                    pil_im = open_image(im_full_path)
+                    im['width'] = pil_im.width
+                    im['height'] = pil_im.height
+                except Exception:
+                    print('Warning: cannot open image {}'.format(im_full_path))
+                    if 'failure' not in im:
+                        im['failure'] = 'Failure image access'
+            # ...if we need to read w/h information
+        # ...for each image
+    # ...if we need to load image sizes
+    ## Generate labelme files
+    print('Generating .json files...')
+    image_id_to_annotations = defaultdict(list)
+    for ann in coco_data['annotations']:
+        image_id_to_annotations[ann['image_id']].append(ann)
+    n_json_files_written = 0
+    n_json_files_error = 0
+    n_json_files_exist = 0
+    # Write output
+    for im in tqdm(coco_data['images']):
+        # Skip this image if it failed to load in whatever system generated this COCO file
+        skip_image = False
+        # Errors are represented differently depending on the source
+        for error_string in ('failure','error'):
+            if (error_string in im) and (im[error_string] is not None):
+                if verbose:
+                    print('Warning: skipping labelme file generation for failed image {}'.format(
+                        im['file_name']))
+                skip_image = True
+                n_json_files_error += 1
+                break
+        if skip_image:
+            continue
+        im_full_path = os.path.join(image_base,im['file_name'])
+        json_path = os.path.splitext(im_full_path)[0] + '.json'
+        if (not overwrite) and (os.path.isfile(json_path)):
+            if verbose:
+                print('Skipping existing file {}'.format(json_path))
+            n_json_files_exist += 1
+            continue
+        annotations_this_image = image_id_to_annotations[im['id']]
+        output_dict = get_labelme_dict_for_image_from_coco_record(im,
+                                                                  annotations_this_image,
+                                                                  coco_data['categories'],
+                                                                  info=None)
+        n_json_files_written += 1
+        with open(json_path,'w') as f:
+            json.dump(output_dict,f,indent=1)
+    # ...for each image
+    print('\nWrote {} .json files (skipped {} for errors, {} because they exist)'.format(
+        n_json_files_written,n_json_files_error,n_json_files_exist))
+# ...def coco_to_labelme()
+#%% Interactive driver
+if False:
+    pass
+    #%% Configure options
+    coco_file = \
+        r'C:\\temp\\snapshot-exploration\\images\\training-images-good\\training-images-good_from_yolo.json'
+    image_folder = os.path.dirname(coco_file)
+    overwrite = True
+    #%% Programmatic execution
+    coco_to_labelme(coco_data=coco_file,image_base=image_folder,overwrite=overwrite)
+    #%% Command-line execution
+    s = 'python coco_to_labelme.py "{}" "{}"'.format(coco_file,image_folder)
+    if overwrite:
+        s += ' --overwrite'
+    print(s)
+    import clipboard; clipboard.copy(s)
+    #%% Opening labelme
+    s = 'python labelme {}'.format(image_folder)
+    print(s)
+    import clipboard; clipboard.copy(s)
+#%% Command-line driver
+import sys,argparse
+def main():
+    parser = argparse.ArgumentParser(
+        description='Convert a COCO database to labelme annotation format')
+    parser.add_argument(
+        'coco_file',
+        type=str,
+        help='Path to COCO data file (.json)')
+    parser.add_argument(
+        'image_base',
+        type=str,
+        help='Path to images (also the output folder)')
+    parser.add_argument(
+        '--overwrite',
+        action='store_true',
+        help='Overwrite existing labelme .json files')
+    if len(sys.argv[1:]) == 0:
+        parser.print_help()
+        parser.exit()
+    args = parser.parse_args()
+    coco_to_labelme(coco_data=args.coco_file,image_base=args.image_base,overwrite=args.overwrite)
+if __name__ == '__main__':
+    main()

megadetector 5.0.7__py3-none-any.whl → 5.0.8__py3-none-any.whl

Potentially problematic release.

megadetector 5.0.7py3-none-any.whl → 5.0.8py3-none-any.whl