megadetector 5.0.24__py3-none-any.whl → 5.0.25__py3-none-any.whl

megadetector/data_management/lila/add_locations_to_island_camera_traps.py

@@ -20,78 +20,82 @@ preview_folder = os.path.expanduser('~/tmp/island_conservation_preview')
 image_directory = os.path.expanduser('~/data/icct/public/')
 
 
-#%% Read input file
+#%% Prevent imports during testing
 
-with open(input_fn,'r') as f:
-    d = json.load(f)
-    
-d['info']
-d['info']['version'] = '1.01'
-
-
-#%% Find locations
-
-images = d['images']
-
-locations = set()
+if False:
 
-for i_image,im in tqdm(enumerate(images),total=len(images)):
-    tokens_fn = im['file_name'].split('/')
-    tokens_id = im['id'].split('_')
-    assert tokens_fn[0] == tokens_id[0]
-    assert tokens_fn[1] == tokens_id[1]
-    location = tokens_fn[0] + '_' + tokens_fn[1]
-    im['location'] = location
-    locations.add(location)
-
-locations = sorted(list(locations))
+    #%% Read input file
     
-for s in locations:
-    print(s)
+    with open(input_fn,'r') as f:
+        d = json.load(f)
+        
+    d['info']
+    d['info']['version'] = '1.01'
     
     
-#%% Write output file
-
-with open(output_fn,'w') as f:
-    json.dump(d,f,indent=1)
+    #%% Find locations
     
-
-#%% Validate .json files
-
-from megadetector.data_management.databases import integrity_check_json_db
-
-options = integrity_check_json_db.IntegrityCheckOptions()
-options.baseDir = image_directory
-options.bCheckImageSizes = False
-options.bCheckImageExistence = True
-options.bFindUnusedImages = True
-
-sorted_categories, data, error_info = integrity_check_json_db.integrity_check_json_db(output_fn, options)
-
-
-#%% Preview labels
-
-from megadetector.visualization import visualize_db
-
-viz_options = visualize_db.DbVizOptions()
-viz_options.num_to_visualize = 2000
-viz_options.trim_to_images_with_bboxes = False
-viz_options.add_search_links = False
-viz_options.sort_by_filename = False
-viz_options.parallelize_rendering = True
-viz_options.classes_to_exclude = ['test']
-html_output_file, image_db = visualize_db.visualize_db(db_path=output_fn,
-                                                         output_dir=preview_folder,
-                                                         image_base_dir=image_directory,
-                                                         options=viz_options)
-
-from megadetector.utils import path_utils
-path_utils.open_file(html_output_file)
-
-
-#%% Zip output file
-
-from megadetector.utils.path_utils import zip_file
-
-zip_file(output_fn, verbose=True)
-assert os.path.isfile(output_fn + '.zip')
+    images = d['images']
+    
+    locations = set()
+    
+    for i_image,im in tqdm(enumerate(images),total=len(images)):
+        tokens_fn = im['file_name'].split('/')
+        tokens_id = im['id'].split('_')
+        assert tokens_fn[0] == tokens_id[0]
+        assert tokens_fn[1] == tokens_id[1]
+        location = tokens_fn[0] + '_' + tokens_fn[1]
+        im['location'] = location
+        locations.add(location)
+    
+    locations = sorted(list(locations))
+        
+    for s in locations:
+        print(s)
+        
+        
+    #%% Write output file
+    
+    with open(output_fn,'w') as f:
+        json.dump(d,f,indent=1)
+        
+    
+    #%% Validate .json files
+    
+    from megadetector.data_management.databases import integrity_check_json_db
+    
+    options = integrity_check_json_db.IntegrityCheckOptions()
+    options.baseDir = image_directory
+    options.bCheckImageSizes = False
+    options.bCheckImageExistence = True
+    options.bFindUnusedImages = True
+    
+    sorted_categories, data, error_info = integrity_check_json_db.integrity_check_json_db(output_fn, options)
+    
+    
+    #%% Preview labels
+    
+    from megadetector.visualization import visualize_db
+    
+    viz_options = visualize_db.DbVizOptions()
+    viz_options.num_to_visualize = 2000
+    viz_options.trim_to_images_with_bboxes = False
+    viz_options.add_search_links = False
+    viz_options.sort_by_filename = False
+    viz_options.parallelize_rendering = True
+    viz_options.classes_to_exclude = ['test']
+    html_output_file, image_db = visualize_db.visualize_db(db_path=output_fn,
+                                                             output_dir=preview_folder,
+                                                             image_base_dir=image_directory,
+                                                             options=viz_options)
+    
+    from megadetector.utils import path_utils
+    path_utils.open_file(html_output_file)
+    
+    
+    #%% Zip output file
+    
+    from megadetector.utils.path_utils import zip_file
+    
+    zip_file(output_fn, verbose=True)
+    assert os.path.isfile(output_fn + '.zip')

megadetector/data_management/lila/add_locations_to_nacti.py

@@ -21,127 +21,131 @@ input_file = r'd:\lila\nacti\nacti_metadata.json.1.13\nacti_metadata.json'
 output_file = r'g:\temp\nacti_metadata.1.14.json'
 
 
-#%% Read metadata
+#%% Prevent execution during testing
 
-with open(input_file,'r') as f:
-    d = json.load(f)
-    
-assert d['info']['version'] == 1.13
-
-
-#%% Map images to locations (according to the metadata)
-
-file_name_to_original_location = {}
-
-# im = dataset_labels['images'][0]
-for im in tqdm(d['images']):
-    file_name_to_original_location[im['file_name']] = im['location']
-
-original_locations = set(file_name_to_original_location.values())
-
-print('Found {} locations in the original metadata:'.format(len(original_locations)))
-for loc in original_locations:
-    print('[{}]'.format(loc))
+if False:
 
-
-#%% Map images to new locations
-
-def path_to_location(relative_path):
-    
-    relative_path = relative_path.replace('\\','/')
-    if relative_path in file_name_to_original_location:
-        location_name = file_name_to_original_location[relative_path]
-        if location_name == 'San Juan Mntns, Colorado':
-            # "part0/sub000/2010_Unit150_Ivan097_img0003.jpg"
-            tokens = relative_path.split('/')[-1].split('_')
-            assert tokens[1].startswith('Unit')
-            location_name = 'sanjuan_{}_{}_{}'.format(tokens[0],tokens[1],tokens[2])
-        elif location_name == 'Lebec, California':
-            # "part0/sub035/CA-03_08_13_2015_CA-03_0009738.jpg"
-            tokens = relative_path.split('/')[-1].split('_')
-            assert tokens[0].startswith('CA-') or tokens[0].startswith('TAG-')
-            location_name = 'lebec_{}'.format(tokens[0])   
-        elif location_name == 'Archbold, FL':
-            # "part1/sub110/FL-01_01_25_2016_FL-01_0040421.jpg"
-            tokens = relative_path.split('/')[-1].split('_')
-            assert tokens[0].startswith('FL-')
-            location_name = 'archbold_{}'.format(tokens[0])   
+    #%% Read metadata
+    
+    with open(input_file,'r') as f:
+        d = json.load(f)
+        
+    assert d['info']['version'] == 1.13
+    
+    
+    #%% Map images to locations (according to the metadata)
+    
+    file_name_to_original_location = {}
+    
+    # im = dataset_labels['images'][0]
+    for im in tqdm(d['images']):
+        file_name_to_original_location[im['file_name']] = im['location']
+    
+    original_locations = set(file_name_to_original_location.values())
+    
+    print('Found {} locations in the original metadata:'.format(len(original_locations)))
+    for loc in original_locations:
+        print('[{}]'.format(loc))
+    
+    
+    #%% Map images to new locations
+    
+    def path_to_location(relative_path):
+        
+        relative_path = relative_path.replace('\\','/')
+        if relative_path in file_name_to_original_location:
+            location_name = file_name_to_original_location[relative_path]
+            if location_name == 'San Juan Mntns, Colorado':
+                # "part0/sub000/2010_Unit150_Ivan097_img0003.jpg"
+                tokens = relative_path.split('/')[-1].split('_')
+                assert tokens[1].startswith('Unit')
+                location_name = 'sanjuan_{}_{}_{}'.format(tokens[0],tokens[1],tokens[2])
+            elif location_name == 'Lebec, California':
+                # "part0/sub035/CA-03_08_13_2015_CA-03_0009738.jpg"
+                tokens = relative_path.split('/')[-1].split('_')
+                assert tokens[0].startswith('CA-') or tokens[0].startswith('TAG-')
+                location_name = 'lebec_{}'.format(tokens[0])   
+            elif location_name == 'Archbold, FL':
+                # "part1/sub110/FL-01_01_25_2016_FL-01_0040421.jpg"
+                tokens = relative_path.split('/')[-1].split('_')
+                assert tokens[0].startswith('FL-')
+                location_name = 'archbold_{}'.format(tokens[0])   
+            else:
+                assert location_name == ''
+                tokens = relative_path.split('/')[-1].split('_')
+                if tokens[0].startswith('CA-') or tokens[0].startswith('TAG-') or tokens[0].startswith('FL-'):
+                    location_name = '{}'.format(tokens[0])
+                
         else:
-            assert location_name == ''
-            tokens = relative_path.split('/')[-1].split('_')
-            if tokens[0].startswith('CA-') or tokens[0].startswith('TAG-') or tokens[0].startswith('FL-'):
-                location_name = '{}'.format(tokens[0])
             
-    else:
+            location_name = 'unknown'    
         
-        location_name = 'unknown'    
+        # print('Returning location {} for file {}'.format(location_name,relative_path))          
     
-    # print('Returning location {} for file {}'.format(location_name,relative_path))          
-
-    return location_name
-
-file_name_to_updated_location = {}
-updated_location_to_count = defaultdict(int)
-for im in tqdm(d['images']):
+        return location_name
     
-    updated_location = path_to_location(im['file_name'])
-    file_name_to_updated_location[im['file_name']] = updated_location
-    updated_location_to_count[updated_location] += 1
-
-updated_location_to_count = {k: v for k, v in sorted(updated_location_to_count.items(), 
-                         key=lambda item: item[1],
-                         reverse=True)}
-
-updated_locations = set(file_name_to_updated_location.values())
-
-print('Found {} updated locations in the original metadata:'.format(len(updated_locations)))
-for loc in updated_location_to_count:
-    print('{}: {}'.format(loc,updated_location_to_count[loc]))
-
-
-#%% Re-write metadata
-
-for im in d['images']:
-    im['location'] = file_name_to_updated_location[im['file_name']]
-d['info']['version'] = 1.14
-
-with open(output_file,'w') as f:
-    json.dump(d,f,indent=1)
+    file_name_to_updated_location = {}
+    updated_location_to_count = defaultdict(int)
+    for im in tqdm(d['images']):
+        
+        updated_location = path_to_location(im['file_name'])
+        file_name_to_updated_location[im['file_name']] = updated_location
+        updated_location_to_count[updated_location] += 1
     
-
-#%% For each location, sample some random images to make sure they look consistent
-
-input_base = r'd:\lila\nacti-unzipped'
-assert os.path.isdir(input_base)
-
-location_to_images = defaultdict(list)
-
-for im in d['images']:
-    location_to_images[im['location']].append(im)
+    updated_location_to_count = {k: v for k, v in sorted(updated_location_to_count.items(), 
+                             key=lambda item: item[1],
+                             reverse=True)}
     
-n_to_sample = 10
-import random
-random.seed(0)
-sampling_folder_base = r'g:\temp\nacti_samples'
-
-for location in tqdm(location_to_images):
+    updated_locations = set(file_name_to_updated_location.values())
     
-    images_this_location = location_to_images[location]
-    if len(images_this_location) > n_to_sample:
-        images_this_location = random.sample(images_this_location,n_to_sample)
-        
-    for i_image,im in enumerate(images_this_location):
+    print('Found {} updated locations in the original metadata:'.format(len(updated_locations)))
+    for loc in updated_location_to_count:
+        print('{}: {}'.format(loc,updated_location_to_count[loc]))
+    
+    
+    #%% Re-write metadata
+    
+    for im in d['images']:
+        im['location'] = file_name_to_updated_location[im['file_name']]
+    d['info']['version'] = 1.14
+    
+    with open(output_file,'w') as f:
+        json.dump(d,f,indent=1)
         
-        fn_relative = im['file_name']
-        source_fn_abs = os.path.join(input_base,fn_relative)
-        assert os.path.isfile(source_fn_abs)
-        ext = os.path.splitext(fn_relative)[1]            
-        target_fn_abs = os.path.join(sampling_folder_base,'{}/{}'.format(
-            location,'image_{}{}'.format(str(i_image).zfill(2),ext)))
-        os.makedirs(os.path.dirname(target_fn_abs),exist_ok=True)
-        shutil.copyfile(source_fn_abs,target_fn_abs)
+    
+    #%% For each location, sample some random images to make sure they look consistent
+    
+    input_base = r'd:\lila\nacti-unzipped'
+    assert os.path.isdir(input_base)
+    
+    location_to_images = defaultdict(list)
+    
+    for im in d['images']:
+        location_to_images[im['location']].append(im)
         
-    # ...for each image
+    n_to_sample = 10
+    import random
+    random.seed(0)
+    sampling_folder_base = r'g:\temp\nacti_samples'
     
-# ...for each location
+    for location in tqdm(location_to_images):
+        
+        images_this_location = location_to_images[location]
+        if len(images_this_location) > n_to_sample:
+            images_this_location = random.sample(images_this_location,n_to_sample)
             
+        for i_image,im in enumerate(images_this_location):
+            
+            fn_relative = im['file_name']
+            source_fn_abs = os.path.join(input_base,fn_relative)
+            assert os.path.isfile(source_fn_abs)
+            ext = os.path.splitext(fn_relative)[1]            
+            target_fn_abs = os.path.join(sampling_folder_base,'{}/{}'.format(
+                location,'image_{}{}'.format(str(i_image).zfill(2),ext)))
+            os.makedirs(os.path.dirname(target_fn_abs),exist_ok=True)
+            shutil.copyfile(source_fn_abs,target_fn_abs)
+            
+        # ...for each image
+        
+    # ...for each location
+                

megadetector/data_management/{wi_to_md.py → speciesnet_to_md.py}

@@ -2,7 +2,7 @@
 
 wi_to_md.py
 
-Converts the WI predictions.json format to MD .json format.  This is just a 
+Converts the WI (SpeciesNet) predictions.json format to MD .json format.  This is just a 
 command-line wrapper around utils.wi_utils.generate_md_results_from_predictions_json.
 
 """
@@ -20,7 +20,7 @@ def main():
     
     parser = argparse.ArgumentParser()
     parser.add_argument('predictions_json_file', action='store', type=str, 
-                        help='.json file to convert from predictions.json format to MD format')
+                        help='.json file to convert from SpeciesNet predictions.json format to MD format')
     parser.add_argument('md_results_file', action='store', type=str, 
                         help='output file to write in MD format')
     parser.add_argument('--base_folder', action='store', type=str, default=None, 

megadetector/detection/run_detector.py

@@ -96,6 +96,7 @@ model_string_to_model_version = {
     'cedar':'v1000.0.0-cedar',
     'larch':'v1000.0.0-larch',
     'default':'v5a.0.0',
+    'default-model':'v5a.0.0',
     'megadetector':'v5a.0.0'
 }
 

megadetector/detection/run_detector_batch.py

@@ -735,7 +735,7 @@ def load_and_run_detector_batch(model_file,
     """
     
     # Validate input arguments
-    if n_cores is None:
+    if n_cores is None or n_cores <= 0:
         n_cores = 1
     
     if confidence_threshold is None:
@@ -1331,13 +1331,14 @@ def main():
     parser.add_argument(
         '--ncores',
         type=int,
-        default=0,
-        help='Number of cores to use for inference; only applies to CPU-based inference')
+        default=1,
+        help='Number of cores to use for inference; only applies to CPU-based inference (default 1)')
     parser.add_argument(
         '--loader_workers',
         type=int,
         default=default_loaders,
-        help='Number of image loader workers to use; only relevant when --use_image_queue is set')
+        help='Number of image loader workers to use; only relevant when --use_image_queue ' + \
+            'is set (default {})'.format(default_loaders))
     parser.add_argument(
         '--class_mapping_filename',
         type=str,