megadetector 5.0.10__py3-none-any.whl → 5.0.12__py3-none-any.whl

{data_management → megadetector/data_management}/lila/create_lila_blank_set.py

@@ -25,10 +25,10 @@ from multiprocessing.pool import ThreadPool
 from urllib.parse import urlparse
 from collections import defaultdict
 
-from data_management.lila.lila_common import read_lila_all_images_file
-from md_utils.url_utils import download_url
-from md_visualization import visualization_utils as vis_utils
-from md_utils.path_utils import recursive_file_list
+from megadetector.data_management.lila.lila_common import read_lila_all_images_file
+from megadetector.utils.url_utils import download_url
+from megadetector.visualization import visualization_utils as vis_utils
+from megadetector.utils.path_utils import recursive_file_list
 
 # We'll write images, metadata downloads, and temporary files here
 lila_local_base = os.path.expanduser('~/lila')
@@ -137,7 +137,7 @@ for i_row,row in tqdm(df.iterrows(),total=len(df)):
 
 #%% Look at the most common labels and common names
 
-from md_utils.ct_utils import sort_dictionary_by_value
+from megadetector.utils.ct_utils import sort_dictionary_by_value
 common_name_to_count = sort_dictionary_by_value(common_name_to_count,reverse=True)
 original_label_to_count = sort_dictionary_by_value(original_label_to_count,reverse=True)
 
@@ -283,7 +283,7 @@ print('Max samples per location: {}'.format(max_blanks_per_location))
 #%% Download those image files (prep)
 
 container_to_url_base = {
-                         'lilablobssc.blob.core.windows.net':'/',
+                         'lilawildlife.blob.core.windows.net':'/lila-wildlide/',
                          'storage.googleapis.com':'/public-datasets-lila/'
                          }
 
@@ -325,13 +325,14 @@ def download_relative_filename(url, output_base, verbose=False, url_base=None, o
     result['status'] = 'success'
     return result
 
+
 def azure_url_to_gcp_http_url(url,error_if_not_azure_url=True):
     """
     Most URLs point to Azure by default, but most files are available on both Azure and GCP.
     This function converts an Azure URL to the corresponding GCP http:// url.
     """
     
-    lila_azure_storage_account = 'https://lilablobssc.blob.core.windows.net'
+    lila_azure_storage_account = 'https://lilawildlife.blob.core.windows.net'
     gcp_bucket_api_url = 'https://storage.googleapis.com/public-datasets-lila'
     error_if_not_azure_url = False
     
@@ -469,7 +470,7 @@ assert len(removed_blank_images_relative) + len(remaining_images) == len(output_
 
 #%% Copy only the confirmed blanks to the confirmed folder
 
-from md_utils.path_utils import is_image_file
+from megadetector.utils.path_utils import is_image_file
 
 all_candidate_blanks = recursive_file_list(candidate_blanks_base,return_relative_paths=True)
 print('Found {} candidate blanks'.format(len(all_candidate_blanks)))
@@ -503,7 +504,7 @@ print('Skipped {} files ({} non-image files)'.format(len(skipped_images_relative
 
 #%% Validate the folder of confirmed blanks
 
-from md_utils.path_utils import find_images
+from megadetector.utils.path_utils import find_images
 # all_confirmed_blanks = recursive_file_list(confirmed_blanks_base,return_relative_paths=True)
 all_confirmed_blanks = find_images(confirmed_blanks_base,return_relative_paths=True,recursive=True)
 assert len(all_confirmed_blanks) < len(all_candidate_blanks)

{data_management → megadetector/data_management}/lila/create_lila_test_set.py

@@ -13,9 +13,10 @@ import json
 import os
 import random
 
-from data_management.lila.lila_common import read_lila_metadata, read_metadata_file_for_dataset
+from megadetector.data_management.lila.lila_common import \
+    read_lila_metadata, read_metadata_file_for_dataset
 
-from md_utils.url_utils import download_url
+from megadetector.utils.url_utils import download_url
 
 n_empty_images_per_dataset = 1
 n_non_empty_images_per_dataset = 1

{data_management → megadetector/data_management}/lila/create_links_to_md_results_files.py

@@ -86,7 +86,7 @@ for i_row,row in df.iterrows():
 
 if validate_urls:
     
-    from md_utils.url_utils import test_urls
+    from megadetector.utils.url_utils import test_urls
     
     urls = set()
     

{data_management → megadetector/data_management}/lila/download_lila_subset.py

@@ -15,7 +15,8 @@ import random
 from tqdm import tqdm
 from collections import defaultdict
 
-from data_management.lila.lila_common import read_lila_all_images_file, is_empty, lila_base_urls
+from megadetector.data_management.lila.lila_common import \
+    read_lila_all_images_file, is_empty, lila_base_urls
 
 for s in lila_base_urls.values():
     assert s.endswith('/')
@@ -102,7 +103,7 @@ else:
 
 #%% Choose target files for each URL
 
-from data_management.lila.lila_common import lila_base_urls
+from megadetector.data_management.lila.lila_common import lila_base_urls
 
 # We have a list of URLs per dataset, flatten that into a single list of URLs
 urls_to_download = set()
@@ -134,7 +135,7 @@ for url in urls_to_download:
 
 #%% Download image files
 
-from md_utils.url_utils import parallel_download_urls
+from megadetector.utils.url_utils import parallel_download_urls
 
 download_results = parallel_download_urls(url_to_target_file=url_to_target_file,
                                           verbose=False,
@@ -161,7 +162,7 @@ if False:
         common_name_to_count[row['common_name']] += 1
         dataset_to_count[row['dataset_name']] += 1
         
-    from md_utils.ct_utils import sort_dictionary_by_value
+    from megadetector.utils.ct_utils import sort_dictionary_by_value
     
     print('Found {} reptiles\n'.format(len(reptile_rows)))
     

{data_management → megadetector/data_management}/lila/generate_lila_per_image_labels.py

@@ -27,13 +27,14 @@ import csv
 from collections import defaultdict
 from tqdm import tqdm
 
-from data_management.lila.lila_common import read_lila_metadata, \
+from megadetector.data_management.lila.lila_common import \
+    read_lila_metadata, \
     read_metadata_file_for_dataset, \
     read_lila_taxonomy_mapping
 
-from md_utils import write_html_image_list
-from md_utils.path_utils import zip_file
-from md_utils.path_utils import open_file
+from megadetector.utils import write_html_image_list
+from megadetector.utils.path_utils import zip_file
+from megadetector.utils.path_utils import open_file
 
 # We'll write images, metadata downloads, and temporary files here
 lila_local_base = os.path.expanduser('~/lila')
@@ -478,7 +479,7 @@ for i_image,image in tqdm(enumerate(images_to_download),total=len(images_to_down
 
 #%% Download images (execution)
 
-from md_utils.url_utils import parallel_download_urls
+from megadetector.utils.url_utils import parallel_download_urls
 download_results = parallel_download_urls(url_to_target_file,verbose=False,overwrite=True,
                                           n_workers=20,pool_type='thread')
 

{data_management → megadetector/data_management}/lila/get_lila_annotation_counts.py

@@ -17,8 +17,8 @@ get_lila_image_counts.py counts the number of *images* for each category in each
 import json
 import os
 
-from data_management.lila.lila_common import read_lila_metadata,\
-    read_metadata_file_for_dataset, read_lila_taxonomy_mapping
+from megadetector.data_management.lila.lila_common import \
+    read_lila_metadata, read_metadata_file_for_dataset, read_lila_taxonomy_mapping
 
 # cloud provider to use for downloading images; options are 'gcp', 'azure', or 'aws'
 preferred_cloud = 'gcp'

{data_management → megadetector/data_management}/lila/get_lila_image_counts.py

@@ -17,7 +17,8 @@ import os
 
 from collections import defaultdict
 
-from data_management.lila.lila_common import read_lila_metadata, read_metadata_file_for_dataset
+from megadetector.data_management.lila.lila_common import \
+    read_lila_metadata, read_metadata_file_for_dataset
 
 # If None, will use all datasets
 datasets_of_interest = None

{data_management → megadetector/data_management}/lila/lila_common.py

@@ -15,9 +15,9 @@ import pandas as pd
 
 from urllib.parse import urlparse
 
-from md_utils.url_utils import download_url
-from md_utils.path_utils import unzip_file
-from md_utils.ct_utils import is_empty
+from megadetector.utils.url_utils import download_url
+from megadetector.utils.path_utils import unzip_file
+from megadetector.utils.ct_utils import is_empty
 
 # LILA camera trap primary metadata file
 lila_metadata_url = 'http://lila.science/wp-content/uploads/2023/06/lila_camera_trap_datasets.csv'
@@ -268,7 +268,7 @@ if False:
     # LILA camera trap primary metadata file
     urls = (lila_metadata_url,lila_taxonomy_mapping_url,lila_all_images_url,wildlife_insights_taxonomy_url)
     
-    from md_utils import url_utils
+    from megadetector.utils import url_utils
     
     status_codes = url_utils.test_urls(urls,timeout=2.0)
     assert all([code == 200 for code in status_codes])
@@ -297,4 +297,4 @@ if False:
                                        pool_type='process',
                                        timeout=2.0)
     assert all([code == 200 for code in status_codes])
-    
+    

{data_management → megadetector/data_management}/lila/test_lila_metadata_urls.py

@@ -16,7 +16,7 @@ Also picks an arbitrary image from each dataset's MD results and make sure the c
 import json
 import os
 
-from data_management.lila.lila_common import read_lila_metadata,\
+from megadetector.data_management.lila.lila_common import read_lila_metadata,\
     read_metadata_file_for_dataset, read_lila_taxonomy_mapping
 
 # We'll write images, metadata downloads, and temporary files here
@@ -115,7 +115,7 @@ for ds_name in metadata_table.keys():
 
 #%% Test URLs
 
-from md_utils.url_utils import test_urls
+from megadetector.utils.url_utils import test_urls
 
 urls_to_test = sorted(url_to_source.keys())
 urls_to_test = [fn.replace('\\','/') for fn in urls_to_test]

{data_management → megadetector/data_management}/ocr_tools.py

@@ -54,11 +54,11 @@ import cv2
 from PIL import Image, ImageFilter
 from tqdm import tqdm
 
-from md_utils.path_utils import find_images
-from md_utils.path_utils import open_file
-from md_utils import write_html_image_list        
-from md_utils.ct_utils import is_iterable
-from md_visualization import visualization_utils as vis_utils
+from megadetector.utils.path_utils import find_images
+from megadetector.utils.path_utils import open_file
+from megadetector.utils import write_html_image_list        
+from megadetector.utils.ct_utils import is_iterable
+from megadetector.visualization import visualization_utils as vis_utils
 
 # pip install pytesseract
 #
@@ -668,7 +668,7 @@ if False:
     
     folder_name = r'g:\temp\island_conservation_camera_traps'
     output_file = r'g:\temp\ocr_results.json'
-    from md_utils.path_utils import insert_before_extension
+    from megadetector.utils.path_utils import insert_before_extension
     output_file = insert_before_extension(output_file)
     n_to_sample = -1
     assert os.path.isdir(folder_name)

{data_management → megadetector/data_management}/read_exif.py

@@ -24,8 +24,8 @@ from multiprocessing.pool import Pool as Pool
 from tqdm import tqdm
 from PIL import Image, ExifTags
 
-from md_utils.path_utils import find_images, is_executable
-from md_utils.ct_utils import args_to_object
+from megadetector.utils.path_utils import find_images, is_executable
+from megadetector.utils.ct_utils import args_to_object
 
 debug_max_images = None
 

{data_management → megadetector/data_management}/remap_coco_categories.py

@@ -81,4 +81,4 @@ def remap_coco_categories(input_data,
 
 #%% Command-line driver
 
-# TODO
+# TODO

{data_management → megadetector/data_management}/remove_exif.py

@@ -63,4 +63,4 @@ def main():
         _ = Parallel(n_jobs=n_exif_threads,verbose=2,prefer='processes')(delayed(remove_exif)(fn) for fn in image_files)
             
 if __name__ == '__main__':
-    main()
+    main()

{data_management → megadetector/data_management}/resize_coco_dataset.py

@@ -16,8 +16,8 @@ import shutil
 from tqdm import tqdm
 from collections import defaultdict
 
-from md_utils.path_utils import insert_before_extension
-from md_visualization.visualization_utils import \
+from megadetector.utils.path_utils import insert_before_extension
+from megadetector.visualization.visualization_utils import \
     open_image, resize_image, exif_preserving_save
 
 
@@ -168,7 +168,7 @@ if False:
     
     #%% Preview
     
-    from md_visualization import visualize_db
+    from megadetector.visualization import visualize_db
     options = visualize_db.DbVizOptions()
     options.parallelize_rendering = True
     options.viz_size = (900, -1)
@@ -179,7 +179,7 @@ if False:
                                               output_folder,options)
     
 
-    from md_utils import path_utils # noqa
+    from megadetector.utils import path_utils # noqa
     path_utils.open_file(html_file)
     
     

{data_management → megadetector/data_management}/wi_download_csv_to_coco.py

@@ -17,8 +17,8 @@ import pandas as pd
 from tqdm import tqdm
 from collections import defaultdict
 
-from md_visualization import visualization_utils as vis_utils
-from md_utils.ct_utils import isnan
+from megadetector.visualization import visualization_utils as vis_utils
+from megadetector.utils.ct_utils import isnan
 
 wi_extra_annotation_columns = \
     ('is_blank','identified_by','wi_taxon_id','class','order','family','genus','species','uncertainty',
@@ -212,7 +212,7 @@ def wi_download_csv_to_coco(csv_file_in,
 
     ##%% Validate output
     
-    from data_management.databases.integrity_check_json_db import \
+    from megadetector.data_management.databases.integrity_check_json_db import \
         IntegrityCheckOptions,integrity_check_json_db
     options = IntegrityCheckOptions()
     options.baseDir = image_folder

{data_management → megadetector/data_management}/yolo_output_to_md_output.py

@@ -44,10 +44,10 @@ import re
 from collections import defaultdict
 from tqdm import tqdm
 
-from md_utils import path_utils
-from md_utils import ct_utils
-from md_visualization import visualization_utils as vis_utils
-from detection.run_detector import CONF_DIGITS, COORD_DIGITS
+from megadetector.utils import path_utils
+from megadetector.utils import ct_utils
+from megadetector.visualization import visualization_utils as vis_utils
+from megadetector.detection.run_detector import CONF_DIGITS, COORD_DIGITS
 
 
 #%% Support functions
@@ -438,4 +438,4 @@ if False:
 
 #%% Command-line driver
 
-# TODO
+# TODO

{data_management → megadetector/data_management}/yolo_to_coco.py

@@ -17,12 +17,12 @@ from functools import partial
 
 from tqdm import tqdm
 
-from md_utils.path_utils import find_images
-from md_utils.path_utils import recursive_file_list
-from md_utils.path_utils import find_image_strings
-from md_utils.ct_utils import invert_dictionary
-from md_visualization.visualization_utils import open_image
-from data_management.yolo_output_to_md_output import read_classes_from_yolo_dataset_file
+from megadetector.utils.path_utils import find_images
+from megadetector.utils.path_utils import recursive_file_list
+from megadetector.utils.path_utils import find_image_strings
+from megadetector.utils.ct_utils import invert_dictionary
+from megadetector.visualization.visualization_utils import open_image
+from megadetector.data_management.yolo_output_to_md_output import read_classes_from_yolo_dataset_file
 
 
 #%% Support functions
@@ -639,7 +639,7 @@ if False:
     
     #%% Check DB integrity
 
-    from data_management.databases import integrity_check_json_db
+    from megadetector.data_management.databases import integrity_check_json_db
 
     options = integrity_check_json_db.IntegrityCheckOptions()
     options.baseDir = input_folder
@@ -652,7 +652,7 @@ if False:
 
     #%% Preview some images
 
-    from md_visualization import visualize_db
+    from megadetector.visualization import visualize_db
 
     viz_options = visualize_db.DbVizOptions()
     viz_options.num_to_visualize = None
@@ -667,7 +667,7 @@ if False:
                                                         image_base_dir=input_folder,
                                                         options=viz_options)
     
-    from md_utils.path_utils import open_file
+    from megadetector.utils.path_utils import open_file
     open_file(html_output_file)
 
 

{detection → megadetector/detection}/process_video.py

@@ -26,16 +26,17 @@ import itertools
 import json
 import shutil
 
-from detection import run_detector_batch
-from md_visualization import visualize_detector_output
-from md_utils.ct_utils import args_to_object
-from detection.video_utils import video_to_frames
-from detection.video_utils import frames_to_video
-from detection.video_utils import frame_results_to_video_results
-from detection.video_utils import video_folder_to_frames
 from uuid import uuid1
 
-from detection.video_utils import default_fourcc
+from megadetector.detection import run_detector_batch
+from megadetector.visualization import visualize_detector_output
+from megadetector.utils.ct_utils import args_to_object
+from megadetector.utils.path_utils import insert_before_extension
+from megadetector.detection.video_utils import video_to_frames
+from megadetector.detection.video_utils import frames_to_video
+from megadetector.detection.video_utils import frame_results_to_video_results
+from megadetector.detection.video_utils import video_folder_to_frames
+from megadetector.detection.video_utils import default_fourcc
 
 
 #%% Classes
@@ -433,8 +434,6 @@ def process_video_folder(options):
             assert len(video_frame_files) > 0, 'Could not find rendered frames for video {}'.format(
                 input_video_file_relative)
             
-            from md_utils.path_utils import insert_before_extension
-            
             # Select the output filename for the rendered video
             if output_folder_is_input_folder:
                 video_output_file = insert_before_extension(input_video_file_abs,'annotated','_')

{detection → megadetector/detection}/pytorch_detector.py

@@ -8,12 +8,14 @@ Module to run MegaDetector v5, a PyTorch YOLOv5 animal detection model.
 
 #%% Imports and constants
 
+import sys
 import torch
 import numpy as np
 import traceback
+import builtins
 
-from detection.run_detector import CONF_DIGITS, COORD_DIGITS, FAILURE_INFER
-from md_utils import ct_utils
+from megadetector.detection.run_detector import CONF_DIGITS, COORD_DIGITS, FAILURE_INFER
+from megadetector.utils import ct_utils
 
 # We support a few ways of accessing the YOLOv5 dependencies:
 #
@@ -44,7 +46,8 @@ try_yolov5_import = True
 # to use more recent YOLOv5 namespace conventions.
 try_ultralytics_import = False
 
-# First try importing from the yolov5 package
+# First try importing from the yolov5 package; this is how the pip
+# package finds YOLOv5 utilities.
 if try_yolov5_import and not utils_imported:
     
     try:
@@ -77,7 +80,7 @@ if try_ultralytics_import and not utils_imported:
         # print('Ultralytics module import failed, falling back to yolov5 import')
         pass
 
-# If we haven't succeeded yet, import from the YOLOv5 repo
+# If we haven't succeeded yet, assume the YOLOv5 repo is on our PYTHONPATH.
 if not utils_imported:
     
     try:
@@ -92,8 +95,9 @@ if not utils_imported:
             from utils.general import scale_boxes as scale_coords
         utils_imported = True
         print('Imported YOLOv5 as utils.*')
-    except ModuleNotFoundError:
-        raise ModuleNotFoundError('Could not import YOLOv5 functions.')
+                
+    except ModuleNotFoundError as e:
+        raise ModuleNotFoundError('Could not import YOLOv5 functions:\n{}'.format(str(e)))
 
 assert utils_imported, 'YOLOv5 import error'
 
@@ -324,10 +328,10 @@ if __name__ == '__main__':
     
     #%%
     
-    import md_visualization.visualization_utils as vis_utils
     import os
+    from megadetector.visualization import visualization_utils as vis_utils
     
-    model_file = 'MDV5A'
+    model_file = os.environ['MDV5A']
     im_file = os.path.expanduser('~/git/MegaDetector/images/nacti.jpg')
 
     detector = PTDetector(model_file)

{detection → megadetector/detection}/run_detector.py

@@ -30,12 +30,14 @@ import statistics
 import sys
 import time
 import warnings
+import tempfile
 
 import humanfriendly
 from tqdm import tqdm
 
-import md_utils.path_utils as path_utils
-import md_visualization.visualization_utils as vis_utils
+from megadetector.utils import path_utils as path_utils
+from megadetector.visualization import visualization_utils as vis_utils
+from megadetector.utils.url_utils import download_url
 
 # ignoring all "PIL cannot read EXIF metainfo for the images" warnings
 warnings.filterwarnings('ignore', '(Possibly )?corrupt EXIF data', UserWarning)
@@ -366,13 +368,13 @@ def load_detector(model_file, force_cpu=False):
     
     start_time = time.time()
     if model_file.endswith('.pb'):
-        from detection.tf_detector import TFDetector
+        from megadetector.detection.tf_detector import TFDetector
         if force_cpu:
             raise ValueError('force_cpu is not currently supported for TF detectors, ' + \
                              'use CUDA_VISIBLE_DEVICES=-1 instead')
         detector = TFDetector(model_file)
     elif model_file.endswith('.pt'):
-        from detection.pytorch_detector import PTDetector
+        from megadetector.detection.pytorch_detector import PTDetector
         detector = PTDetector(model_file, force_cpu, USE_MODEL_NATIVE_CLASSES)        
     else:
         raise ValueError('Unrecognized model format: {}'.format(model_file))
@@ -571,8 +573,6 @@ def download_model(model_name,force_download=False):
             file already exists
     """
     
-    import tempfile
-    from md_utils.url_utils import download_url
     model_tempdir = os.path.join(tempfile.gettempdir(), 'megadetector_models')    
     os.makedirs(model_tempdir,exist_ok=True)
     

{detection → megadetector/detection}/run_detector_batch.py

@@ -5,10 +5,9 @@ run_detector_batch.py
 Module to run MegaDetector on lots of images, writing the results
 to a file in the MegaDetector results format.
 
-https://github.com/agentmorris/MegaDetector/tree/main/api/batch_processing#megadetector-batch-output-format
+https://github.com/agentmorris/MegaDetector/tree/main/megadetector/api/batch_processing#megadetector-batch-output-format
 
-This enables the results to be used in our post-processing pipeline; see
-api/batch_processing/postprocessing/postprocess_batch_results.py .
+This enables the results to be used in our post-processing pipeline; see postprocess_batch_results.py.
 
 This script can save results to checkpoints intermittently, in case disaster
 strikes. To enable this, set --checkpoint_frequency to n > 0, and results 
@@ -66,16 +65,18 @@ from multiprocessing import Process, Manager
 # from multiprocessing.pool import ThreadPool as workerpool
 from multiprocessing.pool import Pool as workerpool
 
-import detection.run_detector as run_detector
-from detection.run_detector import is_gpu_available,\
+from megadetector.detection import run_detector
+from megadetector.detection.run_detector import \
+    is_gpu_available,\
     load_detector,\
     try_download_known_detector,\
     get_detector_version_from_filename,\
     get_detector_metadata_from_version_string
 
-from md_utils import path_utils
-import md_visualization.visualization_utils as vis_utils
-from data_management import read_exif
+from megadetector.utils import path_utils
+from megadetector.visualization import visualization_utils as vis_utils
+from megadetector.data_management import read_exif
+from megadetector.data_management.yolo_output_to_md_output import read_classes_from_yolo_dataset_file
 
 # Numpy FutureWarnings from tensorflow import
 warnings.filterwarnings('ignore', category=FutureWarning)
@@ -287,7 +288,7 @@ def process_images(im_files, detector, confidence_threshold, use_image_queue=Fal
 
     Returns:
         list: list of dicts, in which each dict represents detections on one image,
-        see the 'images' key in https://github.com/agentmorris/MegaDetector/tree/master/api/batch_processing#batch-processing-api-output-format
+        see the 'images' key in https://github.com/agentmorris/MegaDetector/tree/main/megadetector/api/batch_processing#batch-processing-api-output-format
     """
     
     if isinstance(detector, str):
@@ -346,7 +347,7 @@ def process_image(im_file, detector, confidence_threshold, image=None,
     Returns:
         dict: dict representing detections on one image,
         see the 'images' key in 
-        https://github.com/agentmorris/MegaDetector/tree/master/api/batch_processing#batch-processing-api-output-format
+        https://github.com/agentmorris/MegaDetector/tree/main/megadetector/api/batch_processing#batch-processing-api-output-format
     """
     
     if not quiet:
@@ -408,7 +409,6 @@ def _load_custom_class_mapping(class_mapping_filename):
         with open(class_mapping_filename,'r') as f:
             class_mapping = json.load(f)
     elif (class_mapping_filename.endswith('.yml') or class_mapping_filename.endswith('.yaml')):
-        from data_management.yolo_output_to_md_output import read_classes_from_yolo_dataset_file
         class_mapping = read_classes_from_yolo_dataset_file(class_mapping_filename)
         # convert from ints to int-strings
         class_mapping = {str(k):v for k,v in class_mapping.items()}
@@ -730,7 +730,7 @@ def write_results_to_file(results, output_file, relative_path_base=None,
     """
     Writes list of detection results to JSON output file. Format matches:
 
-    https://github.com/agentmorris/MegaDetector/tree/master/api/batch_processing#batch-processing-api-output-format
+    https://github.com/agentmorris/MegaDetector/tree/main/megadetector/api/batch_processing#batch-processing-api-output-format
 
     Args:
         results (list):  list of dict, each dict represents detections on one image