megadetector 5.0.27__py3-none-any.whl → 5.0.29__py3-none-any.whl

megadetector/data_management/resize_coco_dataset.py

@@ -30,9 +30,9 @@ def resize_coco_dataset(input_folder,input_filename,
     """
     Given a COCO-formatted dataset (images in input_folder, data in input_filename), resizes
     all the images to a target size (in output_folder) and scales bounding boxes accordingly.
-    
+
     Args:
-        input_folder (str): the folder where images live; filenames in [input_filename] should 
+        input_folder (str): the folder where images live; filenames in [input_filename] should
             be relative to [input_folder]
         input_filename (str): the (input) COCO-formatted .json file containing annotations
         output_folder (str): the folder to which we should write resized images; can be the
@@ -40,51 +40,51 @@ def resize_coco_dataset(input_folder,input_filename,
         output_filename (str): the COCO-formatted .json file we should generate that refers to
             the resized images
         target_size (list or tuple of ints): this should be tuple/list of ints, with length 2 (w,h).
-            If either dimension is -1, aspect ratio will be preserved.  If both dimensions are -1, this means 
-            "keep the original size".  If  both dimensions are -1 and correct_size_image_handling is copy, this 
-            function is basically a no-op.    
-        correct_size_image_handling (str): can be 'copy' (in which case the original image is just copied 
+            If either dimension is -1, aspect ratio will be preserved.  If both dimensions are -1, this means
+            "keep the original size".  If  both dimensions are -1 and correct_size_image_handling is copy, this
+            function is basically a no-op.
+        correct_size_image_handling (str): can be 'copy' (in which case the original image is just copied
             to the output folder) or 'rewrite' (in which case the image is opened via PIL and re-written,
-            attempting to preserve the same quality).  The only reason to do use 'rewrite' 'is the case where 
-            you're superstitious about biases coming from images in a training set being written by different 
+            attempting to preserve the same quality).  The only reason to do use 'rewrite' 'is the case where
+            you're superstitious about biases coming from images in a training set being written by different
             image encoders.
-   
+
     Returns:
         dict: the COCO database with resized images, identical to the content of [output_filename]
     """
-    
+
     # Read input data
     with open(input_filename,'r') as f:
         d = json.load(f)
-    
+
     # Map image IDs to annotations
     image_id_to_annotations = defaultdict(list)
     for ann in d['annotations']:
         image_id_to_annotations[ann['image_id']].append(ann)
-                                          
+
     # For each image
-    
+
     # TODO: this is trivially parallelizable
     #
     # im = d['images'][0]
     for im in tqdm(d['images']):
-    
+
         input_fn_relative = im['file_name']
         input_fn_abs = os.path.join(input_folder,input_fn_relative)
         assert os.path.isfile(input_fn_abs), "Can't find image file {}".format(input_fn_abs)
-        
+
         output_fn_abs = os.path.join(output_folder,input_fn_relative)
         os.makedirs(os.path.dirname(output_fn_abs),exist_ok=True)
-        
+
         pil_im = open_image(input_fn_abs)
         input_w = pil_im.width
         input_h = pil_im.height
-        
+
         image_is_already_target_size = \
             (input_w == target_size[0]) and (input_h == target_size[1])
         preserve_original_size = \
             (target_size[0] == -1) and (target_size[1] == -1)
-            
+
         # If the image is already the right size...
         if (image_is_already_target_size or preserve_original_size):
             output_w = input_w
@@ -104,18 +104,18 @@ def resize_coco_dataset(input_folder,input_filename,
 
         im['width'] = output_w
         im['height'] = output_h
-        
+
         # For each box
         annotations_this_image = image_id_to_annotations[im['id']]
-        
+
         # ann = annotations_this_image[0]
         for ann in annotations_this_image:
-            
+
             if 'bbox' in ann:
-        
+
                 # boxes are [x,y,w,h]
                 bbox = ann['bbox']
-                
+
                 # Do we need to scale this box?
                 if (output_w != input_w) or (output_h != input_h):
                     width_scale = output_w/input_w
@@ -125,49 +125,49 @@ def resize_coco_dataset(input_folder,input_filename,
                             bbox[1] * height_scale,
                             bbox[2] * width_scale,
                             bbox[3] * height_scale]
-                
+
                 ann['bbox'] = bbox
-            
+
             # ...if this annotation has a box
-    
+
         # ...for each annotation
-    
+
     # ...for each image
-    
+
     # Write output file
     with open(output_filename,'w') as f:
         json.dump(d,f,indent=1)
-    
+
     return d
 
 # ...def resize_coco_dataset(...)
-    
+
 
 #%% Interactive driver
 
 if False:
-    
+
     pass
 
     #%% Test resizing
-        
+
     input_folder = os.path.expanduser('~/data/usgs-tegus/usgs-kissel-training')
     input_filename = os.path.expanduser('~/data/usgs-tegus/usgs-kissel-training.json')
     target_size = (1600,-1)
-    
+
     output_filename = insert_before_extension(input_filename,'resized-test')
     output_folder = input_folder + '-resized-test'
-    
+
     correct_size_image_handling = 'rewrite'
-    
+
     resize_coco_dataset(input_folder,input_filename,
                         output_folder,output_filename,
                         target_size=target_size,
                         correct_size_image_handling=correct_size_image_handling)
-    
-    
+
+
     #%% Preview
-    
+
     from megadetector.visualization import visualize_db
     options = visualize_db.DbVizOptions()
     options.parallelize_rendering = True
@@ -177,12 +177,12 @@ if False:
     html_file,_ = visualize_db.visualize_db(output_filename,
                                               os.path.expanduser('~/tmp/resize_coco_preview'),
                                               output_folder,options)
-    
+
 
     from megadetector.utils import path_utils # noqa
     path_utils.open_file(html_file)
-    
-    
+
+
 #%% Command-line driver
 
 # TODO

megadetector/data_management/speciesnet_to_md.py

@@ -1,41 +1,41 @@
-"""
-
-wi_to_md.py
-
-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.
-
-"""
-
-#%% Imports and constants
-
-import sys
-import argparse
-from megadetector.utils.wi_utils import generate_md_results_from_predictions_json
-
-
-#%% Command-line driver
-
-def main():
-    
-    parser = argparse.ArgumentParser()
-    parser.add_argument('predictions_json_file', action='store', type=str, 
-                        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, 
-                        help='leading string to remove from each path in the predictions.json ' + \
-                            'file (to convert from absolute to relative paths)')
-
-    if len(sys.argv[1:]) == 0:
-        parser.print_help()
-        parser.exit()
-            
-    args = parser.parse_args()
-    
-    generate_md_results_from_predictions_json(args.predictions_json_file,
-                                              args.md_results_file,
-                                              args.base_folder)
-
-if __name__ == '__main__':    
-    main()
+"""
+
+speciesnet_to_md.py
+
+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.
+
+"""
+
+#%% Imports and constants
+
+import sys
+import argparse
+from megadetector.utils.wi_utils import generate_md_results_from_predictions_json
+
+
+#%% Command-line driver
+
+def main(): # noqa
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument('predictions_json_file', action='store', type=str,
+                        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,
+                        help='leading string to remove from each path in the predictions.json ' + \
+                            'file (to convert from absolute to relative paths)')
+
+    if len(sys.argv[1:]) == 0:
+        parser.print_help()
+        parser.exit()
+
+    args = parser.parse_args()
+
+    generate_md_results_from_predictions_json(args.predictions_json_file,
+                                              args.md_results_file,
+                                              args.base_folder)
+
+if __name__ == '__main__':
+    main()

megadetector/data_management/wi_download_csv_to_coco.py

@@ -27,7 +27,7 @@ wi_extra_annotation_columns = \
 
 wi_extra_image_columns = ('project_id','deployment_id')
 
-def _make_location_id(project_id,deployment_id):    
+def _make_location_id(project_id,deployment_id):
     return 'project_' + str(project_id) + '_deployment_' + deployment_id
 
 default_category_remappings = {
@@ -47,86 +47,86 @@ def wi_download_csv_to_coco(csv_file_in,
                             verbose=True,
                             category_remappings=default_category_remappings):
     """
-    Converts a .csv file from a Wildlife Insights project export to a COCO 
+    Converts a .csv file from a Wildlife Insights project export to a COCO
     Camera Traps .json file.
-    
+
     Args:
         csv_file_in (str): the downloaded .csv file we should convert to COCO
-        coco_file_out (str, optional): the .json file we should write; if [coco_file_out] is None, 
+        coco_file_out (str, optional): the .json file we should write; if [coco_file_out] is None,
             uses [csv_file_in].json
-        image_folder (str, optional): the folder where images live, only relevant if 
+        image_folder (str, optional): the folder where images live, only relevant if
             [validate_images] is True
         validate_images (bool, optional): whether to check images for corruption and load
             image sizes; if this is True, [image_folder] must be a valid folder
-        gs_prefix (str, optional): a string to remove from GS URLs to convert to path names... 
+        gs_prefix (str, optional): a string to remove from GS URLs to convert to path names...
             for example, if your gs:// URLs look like:
-    
+
             `gs://11234134_xyz/deployment/55554/dfadfasdfs.jpg`
-    
+
             ...and you specify gs_prefix='11234134_xyz/deployment/', the filenames in
             the .json file will look like:
-        
+
             `55554/dfadfasdfs.jpg`
         verbose (bool, optional): enable additional debug console output
         category_remappings (dict, optional): str --> str dict that maps any number of
             WI category names to output category names; for example defaults to mapping
-            "Homo Species" to "Human", but leaves 99.99% of categories unchanged.        
-            
-    Returns: 
+            "Homo Species" to "Human", but leaves 99.99% of categories unchanged.
+
+    Returns:
         dict: COCO-formatted data, identical to what's written to [coco_file_out]
     """
-    
+
     ##%% Create COCO dictionaries
-    
+
     category_name_to_id = {}
     category_name_to_id['empty'] = 0
-    
+
     df = pd.read_csv(csv_file_in)
-    
+
     print('Read {} rows from {}'.format(len(df),csv_file_in))
-    
+
     image_id_to_image = {}
     image_id_to_annotations = defaultdict(list)
-    
+
     # i_row = 0; row = df.iloc[i_row]
     for i_row,row in df.iterrows():
-        
+
         image_id = row['image_id']
-        
+
         if image_id not in image_id_to_image:
-            
+
             im = {}
             image_id_to_image[image_id] = im
-            
+
             im['id'] = image_id
-            
+
             gs_url = row['location']
             assert gs_url.startswith('gs://')
-            
+
             file_name = gs_url.replace('gs://','')
             if gs_prefix is not None:
                 file_name = file_name.replace(gs_prefix,'')
-                
+
             location_id = _make_location_id(row['project_id'],row['deployment_id'])
             im['file_name'] = file_name
             im['location'] = location_id
             im['datetime'] = row['timestamp']
-            
+
             im['wi_image_info'] = {}
             for s in wi_extra_image_columns:
                 im['wi_image_info'][s] = str(row[s])
-            
+
         else:
-            
+
             im = image_id_to_image[image_id]
             assert im['datetime'] == row['timestamp']
             location_id = _make_location_id(row['project_id'],row['deployment_id'])
             assert im['location'] == location_id
-            
+
         category_name = row['common_name']
         if category_remappings is not None and category_name in category_remappings:
             category_name = category_remappings[category_name]
-            
+
         if category_name == 'Blank':
             category_name = 'empty'
             assert row['is_blank'] == 1
@@ -138,24 +138,24 @@ def wi_download_csv_to_coco(csv_file_in,
         else:
             category_id = len(category_name_to_id)
             category_name_to_id[category_name] = category_id
-        
+
         ann = {}
         ann['image_id'] = image_id
         annotations_this_image = image_id_to_annotations[image_id]
         annotation_number = len(annotations_this_image)
-        ann['id'] = image_id + '_' + str(annotation_number).zfill(2)        
+        ann['id'] = image_id + '_' + str(annotation_number).zfill(2)
         ann['category_id'] = category_id
         annotations_this_image.append(ann)
-        
+
         extra_info = {}
-        for s in wi_extra_annotation_columns:            
+        for s in wi_extra_annotation_columns:
             v = row[s]
             if not isnan(v):
                 extra_info[s] = v
         ann['wi_extra_info'] = extra_info
-        
+
     # ...for each row
-    
+
     images = list(image_id_to_image.values())
     categories = []
     for category_name in category_name_to_id:
@@ -173,25 +173,25 @@ def wi_download_csv_to_coco(csv_file_in,
     coco_data['images'] = images
     coco_data['annotations'] = annotations
     coco_data['categories'] = categories
-    
-    
-    ##%% Validate images, add sizes        
-    
+
+
+    ##%% Validate images, add sizes
+
     if validate_images:
-        
+
         print('Validating images')
-        
+
         assert os.path.isdir(image_folder), \
             'Must specify a valid image folder if you specify validate_images=True'
-        
+
         # TODO: trivially parallelizable
-        #    
+        #
         # im = images[0]
         for im in tqdm(images):
             file_name_relative = im['file_name']
             file_name_abs = os.path.join(image_folder,file_name_relative)
             assert os.path.isfile(file_name_abs)
-                
+
             im['corrupt'] = False
             try:
                 pil_im = vis_utils.load_image(file_name_abs)
@@ -200,19 +200,19 @@ def wi_download_csv_to_coco(csv_file_in,
             if not im['corrupt']:
                 im['width'] = pil_im.width
                 im['height'] = pil_im.height
-    
-    
+
+
     ##%% Write output json
-        
-    if coco_file_out is None:        
+
+    if coco_file_out is None:
         coco_file_out = csv_file_in + '.json'
-        
+
     with open(coco_file_out,'w') as f:
         json.dump(coco_data,f,indent=1)
 
 
     ##%% Validate output
-    
+
     from megadetector.data_management.databases.integrity_check_json_db import \
         IntegrityCheckOptions,integrity_check_json_db
     options = IntegrityCheckOptions()
@@ -220,18 +220,18 @@ def wi_download_csv_to_coco(csv_file_in,
     options.bCheckImageExistence = True
     options.verbose = verbose
     _ = integrity_check_json_db(coco_file_out,options)
-    
+
     return coco_data
 
-# ...def wi_download_csv_to_coco(...)    
+# ...def wi_download_csv_to_coco(...)
 
 
 #%% Interactive driver
 
 if False:
-    
+
     #%%
-    
+
     base_folder = r'a/b/c'
     csv_file_in = os.path.join(base_folder,'images.csv')
     coco_file_out = None