Merge branch 'main' into m1support

.gitignore

@@ -53,3 +53,9 @@ api_config*.py
 *.pth
 *.o
 debug.log
+*.swp
+
+# Things created when building the sync API
+yolov5
+api/synchronous/api_core/animal_detection_api/detection
+

README.md

@@ -35,7 +35,7 @@ If you're already familiar with MegaDetector and you're ready to run it on your
 
 We work with ecologists all over the world to help them spend less time annotating images and more time thinking about conservation.  You can read a little more about how this works on our [getting started with MegaDetector](collaborations.md) page.
 
-Here are a few of the organizations that have used MegaDetector... we're only listing organizations who (a) we know about and (b) have kindly given us permission to refer to them here, so if you're using MegaDetector or other tools from this repo and would like to be added to this list, <a href="mailto:cameratraps@lila.science">email us</a>!
+Here are a few of the organizations that have used MegaDetector... we're only listing organizations who (a) we know about and (b) have kindly given us permission to refer to them here (or have posted publicly about their use of MegaDetector), so if you're using MegaDetector or other tools from this repo and would like to be added to this list, <a href="mailto:cameratraps@lila.science">email us</a>!
 
 * Idaho Department of Fish and Game
 * San Diego Zoo Global
@@ -76,7 +76,6 @@ Here are a few of the organizations that have used MegaDetector... we're only li
 * Conservation X Labs
 * The Nature Conservancy in Wyoming
 * Seattle Urban Carnivore Project
-* Road Ecology Center, University of California, Davis
 * Blackbird Environmental
 * UNSW Sydney
 * Taronga Conservation Society
@@ -85,13 +84,15 @@ Here are a few of the organizations that have used MegaDetector... we're only li
 * Capitol Reef National Park and Utah Valley University
 * University of Victoria Applied Conservation Macro Ecology (ACME) Lab 
 * Université du Québec en Outaouais Institut des Science de la Forêt Tempérée (ISFORT)
-* University of British Columbia Wildlife Coexistence Lab ([OSS tool](https://github.com/WildCoLab/WildCo_Face_Blur))
-* Alberta Biodiversity Monitoring Institute (ABMI) ([blog post](https://wildcams.ca/blog/the-abmi-visits-the-zoo/))
-* Felidae Conservation Fund ([platform](https://wildepod.org/)) ([blog post](https://abhaykashyap.com/blog/ai-powered-camera-trap-image-annotation-system/))
+* University of British Columbia Wildlife Coexistence Lab ([WildCo-FaceBlur tool](https://github.com/WildCoLab/WildCo_Face_Blur))
+* Road Ecology Center, University of California, Davis ([Wildlife Observer Network platform](https://wildlifeobserver.net/))
+* The Nature Conservancy in California ([Animl platform](https://github.com/tnc-ca-geo/animl-frontend))
+* Felidae Conservation Fund ([WildePod platform](https://wildepod.org/)) ([blog post](https://abhaykashyap.com/blog/ai-powered-camera-trap-image-annotation-system/))
+* Alberta Biodiversity Monitoring Institute (ABMI) ([WildTrax platform](https://www.wildtrax.ca/)) ([blog post](https://wildcams.ca/blog/the-abmi-visits-the-zoo/))
+* Shan Shui Conservation Center ([blog post](https://mp.weixin.qq.com/s/iOIQF3ckj0-rEG4yJgerYw?fbclid=IwAR0alwiWbe3udIcFvqqwm7y5qgr9hZpjr871FZIa-ErGUukZ7yJ3ZhgCevs)) ([translated blog post](https://mp-weixin-qq-com.translate.goog/s/iOIQF3ckj0-rEG4yJgerYw?fbclid=IwAR0alwiWbe3udIcFvqqwm7y5qgr9hZpjr871FZIa-ErGUukZ7yJ3ZhgCevs&_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en&_x_tr_pto=wapp))
 * Irvine Ranch Conservancy ([story](https://www.ocregister.com/2022/03/30/ai-software-is-helping-researchers-focus-on-learning-about-ocs-wild-animals/))
 * Wildlife Protection Solutions ([story](https://customers.microsoft.com/en-us/story/1384184517929343083-wildlife-protection-solutions-nonprofit-ai-for-earth))
 * [TrapTagger](https://wildeyeconservation.org/trap-tagger-about/)
-* [WildTrax](https://www.wildtrax.ca/)
 * [Camelot](https://camelotproject.org/)
 
 # Data

api/batch_processing/data_preparation/manage_local_batch.py

@@ -46,6 +46,9 @@
 
 quiet_mode = True
 
+# Specify a target image size when running MD... strongly recommended to leave this at "None"
+image_size = None
+
 # Only relevant when running on CPU
 ncores = 1
 
@@ -94,7 +97,7 @@
 
 filename_base = os.path.join(base_output_folder_name, base_task_name)
 combined_api_output_folder = os.path.join(filename_base, 'combined_api_outputs')
-postprocessing_output_folder = os.path.join(filename_base, 'postprocessing')
+postprocessing_output_folder = os.path.join(filename_base, 'preview')
 
 os.makedirs(filename_base, exist_ok=True)
 os.makedirs(combined_api_output_folder, exist_ok=True)
@@ -181,9 +184,13 @@ def split_list(L, n):
     if quiet_mode:
         quiet_string = '--quiet'
 
+    image_size_string = ''
+    if image_size is not None:
+        image_size_string = '--image_size {}'.format(image_size)
+
     # Generate the script to run MD
 
-    cmd = f'{cuda_string} python run_detector_batch.py "{model_file}" "{chunk_file}" "{output_fn}" {checkpoint_frequency_string} {checkpoint_path_string} {use_image_queue_string} {ncores_string} {quiet_string}'
+    cmd = f'{cuda_string} python run_detector_batch.py "{model_file}" "{chunk_file}" "{output_fn}" {checkpoint_frequency_string} {checkpoint_path_string} {use_image_queue_string} {ncores_string} {quiet_string} {image_size_string}'
 
     cmd_file = os.path.join(filename_base,'run_chunk_{}_gpu_{}.sh'.format(str(i_task).zfill(2),
                             str(gpu_number).zfill(2)))
@@ -255,7 +262,8 @@ def split_list(L, n):
                                               results=None,
                                               n_cores=ncores, 
                                               use_image_queue=use_image_queue,
-                                              quiet=quiet_mode)        
+                                              quiet=quiet_mode,
+                                              image_size=image_size)        
         elapsed = time.time() - start_time
 
         print('Task {}: finished inference for {} images in {}'.format(
@@ -338,7 +346,9 @@ def split_list(L, n):
     assert task_results['detection_categories'] == combined_results['detection_categories']
     combined_results['images'].extend(copy.deepcopy(task_results['images']))
 
-assert len(combined_results['images']) == len(all_images)
+assert len(combined_results['images']) == len(all_images), \
+    'Expected {} images in combined results, found {}'.format(
+        len(all_images),len(combined_results['images']))
 
 result_filenames = [im['file'] for im in combined_results['images']]
 assert len(combined_results['images']) == len(set(result_filenames))
@@ -1218,7 +1228,41 @@ def remove_overflow_folders(relativePath):
 d = categorize_detections_by_size.categorize_detections_by_size(input_file,size_separated_file,options)
 
 
-#%% Subsetting
+#%% .json splitting
+
+data = None
+
+from api.batch_processing.postprocessing.subset_json_detector_output import (
+    subset_json_detector_output, SubsetJsonDetectorOutputOptions)
+
+input_filename = filtered_output_filename
+output_base = os.path.join(filename_base,'json_subsets')
+
+if False:
+    if data is None:
+        with open(input_filename) as f:
+            data = json.load(f)
+    print('Data set contains {} images'.format(len(data['images'])))
+
+print('Processing file {} to {}'.format(input_filename,output_base))          
+
+options = SubsetJsonDetectorOutputOptions()
+# options.query = None
+# options.replacement = None
+
+options.split_folders = True
+options.make_folder_relative = True
+
+# Reminder: 'n_from_bottom' with a parameter of zero is the same as 'bottom'
+options.split_folder_mode = 'bottom'  # 'top', 'n_from_top', 'n_from_bottom'
+options.split_folder_param = 0
+options.overwrite_json_files = False
+options.confidence_threshold = 0.01
+
+subset_data = subset_json_detector_output(input_filename, output_base, options, data)
+
+
+#%% Custom splitting/subsetting
 
 data = None
 
@@ -1246,9 +1290,11 @@ def remove_overflow_folders(relativePath):
     options = SubsetJsonDetectorOutputOptions()
     options.confidence_threshold = 0.01
     options.overwrite_json_files = True
-    options.make_folder_relative = True
-    options.query = folder_name + '\\'
+    options.query = folder_name + '/'
 
+    # This doesn't do anything in this case, since we're not splitting folders
+    # options.make_folder_relative = True        
+
     subset_data = subset_json_detector_output(input_filename, output_filename, options, data)
 
 
@@ -1268,13 +1314,13 @@ def remove_overflow_folders(relativePath):
 subset_json_detector_output(input_filename,output_filename,options)
 
 
-#%% Folder splitting
+#%% Splitting images into folders
 
 from api.batch_processing.postprocessing.separate_detections_into_folders import (
     separate_detections_into_folders, SeparateDetectionsIntoFoldersOptions)
 
 default_threshold = 0.2
-base_output_folder = r'e:\{}-{}-separated'.format(base_task_name,default_threshold)
+base_output_folder = os.path.expanduser('~/data/{}-{}-separated'.format(base_task_name,default_threshold))
 
 options = SeparateDetectionsIntoFoldersOptions(default_threshold)
 

api/batch_processing/postprocessing/separate_detections_into_folders.py

@@ -416,6 +416,10 @@ def separate_detections_into_folders(options):
         if 'detector_metadata' in results['info'] and \
             'typical_detection_threshold' in results['info']['detector_metadata']:
             default_threshold = results['info']['detector_metadata']['typical_detection_threshold']
+        elif ('detector' not in results['info']) or (results['info']['detector'] is None):
+            print('Warning: detector version not available in results file, using MDv5 defaults')
+            detector_metadata = get_detector_metadata_from_version_string('v5a.0.0')
+            default_threshold = detector_metadata['typical_detection_threshold']
         else:
             print('Warning: detector metadata not available in results file, inferring from MD version')
             detector_filename = results['info']['detector']
@@ -634,6 +638,24 @@ def main():
 
     args_to_object(args, options)
 
+    def validate_threshold(v,name):
+        print('{} {}'.format(v,name))
+        if v is not None:
+            assert v >= 0.0 and v <= 1.0, \
+                'Illegal {} threshold {}'.format(name,v)
+
+    validate_threshold(args.threshold,'default')
+    validate_threshold(args.animal_threshold,'animal')
+    validate_threshold(args.vehicle_threshold,'vehicle')
+    validate_threshold(args.human_threshold,'human')
+
+    if args.threshold is not None:
+        if args.animal_threshold is not None \
+            and args.human_threshold is not None \
+            and args.vehicle_threshold is not None:
+                raise ValueError('Default threshold specified, but all category thresholds also specified... not exactly wrong, but it\'s likely that you meant something else.')        
+
+
     options.category_name_to_threshold['animal'] = args.animal_threshold
     options.category_name_to_threshold['person'] = args.human_threshold
     options.category_name_to_threshold['vehicle'] = args.vehicle_threshold