megadetector 5.0.15__py3-none-any.whl → 5.0.17__py3-none-any.whl

megadetector/utils/url_utils.py

@@ -75,7 +75,8 @@ def download_url(url,
                  destination_filename=None, 
                  progress_updater=None, 
                  force_download=False, 
-                 verbose=True):
+                 verbose=True,
+                 escape_spaces=True):
     """
     Downloads a URL to a file.  If no file is specified, creates a temporary file, 
     making a best effort to avoid filename collisions.
@@ -92,6 +93,7 @@ def download_url(url,
         force_download (bool, optional): download this file even if [destination_filename]
             exists.
         verbose (bool, optional): enable additional debug console output
+        escape_spaces (bool, optional): replace ' ' with '%20'
         
     Returns:
         str: the filename to which [url] was downloaded, the same as [destination_filename]
@@ -107,6 +109,7 @@ def download_url(url,
     url_no_sas = url.split('?')[0]
         
     if destination_filename is None:
+        
         target_folder = get_temp_folder()
         url_without_sas = url.split('?', 1)[0]
         
@@ -119,6 +122,9 @@ def download_url(url,
         destination_filename = \
             os.path.join(target_folder,url_as_filename)
         
+    if escape_spaces:
+        url = url.replace(' ','%20')
+        
     if (not force_download) and (os.path.isfile(destination_filename)):
         if verbose:
             print('Bypassing download of already-downloaded file {}'.format(os.path.basename(url_no_sas)))
@@ -135,6 +141,8 @@ def download_url(url,
         
     return destination_filename
 
+# ...def download_url(...)
+
 
 def download_relative_filename(url, output_base, verbose=False):
     """
@@ -162,6 +170,8 @@ def download_relative_filename(url, output_base, verbose=False):
     destination_filename = os.path.join(output_base,relative_filename)
     return download_url(url, destination_filename, verbose=verbose)
 
+# ...def download_relative_filename(...)
+
 
 def _do_parallelized_download(download_info,overwrite=False,verbose=False):
     """
@@ -191,6 +201,8 @@ def _do_parallelized_download(download_info,overwrite=False,verbose=False):
     result['status'] = 'success'
     return result
 
+# ...def _do_parallelized_download(...)
+
 
 def parallel_download_urls(url_to_target_file,verbose=False,overwrite=False,
                            n_workers=20,pool_type='thread'):
@@ -251,8 +263,10 @@ def parallel_download_urls(url_to_target_file,verbose=False,overwrite=False,
                 
     return results
 
-    
-def test_url(url, error_on_failure=True, timeout=None):
+# ...def parallel_download_urls(...)
+
+
+def test_url(url,error_on_failure=True,timeout=None):
     """
     Tests the availability of [url], returning an http status code.
     
@@ -275,7 +289,7 @@ def test_url(url, error_on_failure=True, timeout=None):
     return r.status_code
     
 
-def test_urls(urls, error_on_failure=True, n_workers=1, pool_type='thread', timeout=None):
+def test_urls(urls,error_on_failure=True,n_workers=1,pool_type='thread',timeout=None):
     """
     Verify that URLs are available (i.e., returns status 200).  By default,
     errors if any URL is unavailable.  
@@ -321,3 +335,86 @@ def test_urls(urls, error_on_failure=True, n_workers=1, pool_type='thread', time
             urls), total=len(urls)))
                 
     return status_codes
+
+# ...def test_urls(...)
+
+
+def get_url_size(url,verbose=False,timeout=None):
+    """
+    Get the size of the file pointed to by a URL, based on the Content-Length property.  If the 
+    URL is not available, or the Content-Length property is not available, or the content-Length 
+    property is not an integer, returns None.  
+    
+    Args:
+        url (str): the url to test
+        verbose (bool, optional): enable additional debug output
+        timeout (int, optional): timeout in seconds to wait before considering this 
+            access attempt to be a failure; see requests.head() for precise documentation
+        
+    Returns:
+        int: the file size in bytes, or None if it can't be retrieved
+    """
+
+    try:
+        r = urllib.request.Request(url,method='HEAD')
+        f = urllib.request.urlopen(r, timeout=timeout)
+        if f.status != 200:
+            if verbose:
+                print('Status {} retrieving file size for {}'.format(f.status,url))
+            return None
+        size_bytes = int(f.headers['Content-Length'])
+        return size_bytes
+    except Exception as e:
+        if verbose:
+            print('Error retrieving file size for {}:\n{}'.format(url,str(e)))
+        return None
+    
+# ...def get_url_size(...)
+
+
+def get_url_sizes(urls,n_workers=1,pool_type='thread',timeout=None,verbose=False):
+    """
+    Retrieve file sizes for the URLs specified by [urls].  Returns None for any URLs
+    that we can't access, or URLs for which the Content-Length property is not set.
+    
+    Args:
+        urls (list): list of URLs for which we should retrieve sizes
+        n_workers (int, optional): number of concurrent workers, set to <=1 to disable
+            parallelization
+        pool_type (str, optional): worker type to use; should be 'thread' or 'process'
+        timeout (int, optional): timeout in seconds to wait before considering this 
+            access attempt to be a failure; see requests.head() for precise documentation
+        verbose (bool, optional): print additional debug information
+    
+    Returns:
+        dict: maps urls to file sizes, which will be None for URLs for which we were unable
+        to retrieve a valid size.        
+    """
+        
+    url_to_size = {}
+    
+    if n_workers <= 1:        
+        
+        for url in tqdm(urls):
+            url_to_size[url] = get_url_size(url,verbose=verbose,timeout=timeout)
+                
+    else:
+
+        if pool_type == 'thread':
+            pool = ThreadPool(n_workers)
+        else:
+            assert pool_type == 'process', 'Unsupported pool type {}'.format(pool_type)
+            pool = Pool(n_workers)
+        
+        print('Starting a {} pool with {} workers'.format(pool_type,n_workers))
+        
+        file_sizes = list(tqdm(pool.imap(
+            partial(get_url_size,verbose=verbose,timeout=timeout),
+            urls), total=len(urls)))
+        
+        for i_url,url in enumerate(urls):
+            url_to_size[url] = file_sizes[i_url]
+                
+    return url_to_size
+
+# ...get_url_sizes(...)

megadetector/visualization/visualization_utils.py

@@ -536,6 +536,9 @@ def render_detection_bounding_boxes(detections,
             
             x1, y1, w_box, h_box = detection['bbox']
             display_boxes.append([y1, x1, y1 + h_box, x1 + w_box])
+            
+            # The class index to use for coloring this box, which may be based on the detection
+            # category or on the most confident classification category.
             clss = detection['category']
             
             # {} is the default, which means "show labels with no mapping", so don't use "if label_map" here
@@ -558,22 +561,30 @@ def render_detection_bounding_boxes(detections,
                         assert len(displayed_label) == 1
                         displayed_label[0] += ' ' + custom_string
                                     
-            if 'classifications' in detection:
+            if ('classifications' in detection) and len(detection['classifications']) > 0:
 
-                # To avoid duplicate colors with detection-only visualization, offset
-                # the classification class index by the number of detection classes
-                clss = annotation_constants.NUM_DETECTOR_CATEGORIES + int(detection['classifications'][0][0])
                 classifications = detection['classifications']
+                
                 if len(classifications) > max_classifications:
                     classifications = classifications[0:max_classifications]
                     
+                max_classification_category = 0
+                max_classification_conf = -100
+                
                 for classification in classifications:
                     
                     classification_conf = classification[1]
-                    if classification_conf is not None and \
-                        classification_conf < classification_confidence_threshold:
+                    if classification_conf is None or \
+                       classification_conf < classification_confidence_threshold:
                         continue
+                    
                     class_key = classification[0]
+                    
+                    # Is this the most confident classification for this detection?
+                    if classification_conf > max_classification_conf:
+                        max_classification_conf = classification_conf
+                        max_classification_category = int(class_key)
+                        
                     if (classification_label_map is not None) and (class_key in classification_label_map):
                         class_name = classification_label_map[class_key]
                     else:
@@ -585,6 +596,10 @@ def render_detection_bounding_boxes(detections,
                     
                 # ...for each classification
 
+                # To avoid duplicate colors with detection-only visualization, offset
+                # the classification class index by the number of detection classes
+                clss = annotation_constants.NUM_DETECTOR_CATEGORIES + max_classification_category
+                
             # ...if we have classification results
                         
             display_strs.append(displayed_label)

megadetector/visualization/visualize_db.py

@@ -122,6 +122,14 @@ class DbVizOptions:
         
         #: Enable additionald debug console output
         self.verbose = False
+        
+        #: COCO files used for evaluation may contain confidence scores, this
+        #: determines the field name used for confidence scores
+        self.confidence_field_name = 'score'
+        
+        #: Optionally apply a confidence threshold; this requires that [confidence_field_name] 
+        #: be present in all detections.
+        self.confidence_threshold = None
     
 
 #%% Helper functions
@@ -294,6 +302,14 @@ def visualize_db(db_path, output_dir, image_base_dir, options=None):
         # iAnn = 0; anno = annos_i.iloc[iAnn]
         for iAnn,anno in annos_i.iterrows():
         
+            if options.confidence_threshold is not None:
+                assert options.confidence_field_name in anno, \
+                    'Error: confidence thresholding requested, ' + \
+                        'but at least one annotation does not have the {} field'.format(
+                            options.confidence_field_name)
+                if anno[options.confidence_field_name] < options.confidence_threshold:
+                    continue
+                
             if 'sequence_level_annotation' in anno:
                 bSequenceLevelAnnotation = anno['sequence_level_annotation']
                 if bSequenceLevelAnnotation:

{megadetector-5.0.15.dist-info → megadetector-5.0.17.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: megadetector
-Version: 5.0.15
+Version: 5.0.17
 Summary: MegaDetector is an AI model that helps conservation folks spend less time doing boring things with camera trap images.
 Author-email: Your friendly neighborhood MegaDetector team <cameratraps@lila.science>
 Maintainer-email: Your friendly neighborhood MegaDetector team <cameratraps@lila.science>
@@ -54,25 +54,23 @@ Requires-Dist: ultralytics-yolov5 ==0.1.1
 
 This package is a pip-installable version of the support/inference code for [MegaDetector](https://github.com/agentmorris/MegaDetector/?tab=readme-ov-file#megadetector), an object detection model that helps conservation biologists spend less time doing boring things with camera trap images.  Complete documentation for this Python package is available at [megadetector.readthedocs.io](https://megadetector.readthedocs.io).
 
-If you aren't looking for the Python package specificaly, and you just want to learn more about what MegaDetector is all about, head over to the [MegaDetector repo](https://github.com/agentmorris/MegaDetector/?tab=readme-ov-file#megadetector).
+If you aren't looking for the Python package specifically, and you just want to learn more about what MegaDetector is all about, head over to the [MegaDetector repo](https://github.com/agentmorris/MegaDetector/?tab=readme-ov-file#megadetector).
 
 
-## Reasons you probably aren't looking for this package
+## Reasons might not be looking for this package
 
 ### If you are an ecologist...
 
-If you are an ecologist looking to use MegaDetector to help you get through your camera trap images, you probably don't want this package.  We recommend starting with our "[Getting started with MegaDetector](https://github.com/agentmorris/MegaDetector/blob/main/getting-started.md)" page, then digging in to the [MegaDetector User Guide](https://github.com/agentmorris/MegaDetector/blob/main/megadetector.md), which will walk you through the process of using MegaDetector.  That journey will <i>not</i> involve this Python package.
+If you are an ecologist looking to use MegaDetector to help you get through your camera trap images, you probably don't want this package, or at least you probably don't want to start at this page.  We recommend starting with our "[Getting started with MegaDetector](https://github.com/agentmorris/MegaDetector/blob/main/getting-started.md)" page, then digging in to the [MegaDetector User Guide](https://github.com/agentmorris/MegaDetector/blob/main/megadetector.md), which will walk you through the process of using MegaDetector.
 
 ### If you are a computer-vision-y type...
 
-If you are a computer-vision-y person looking to run or fine-tune MegaDetector programmatically, you still probably don't want this package.  MegaDetector is just a fine-tuned version of [YOLOv5](https://github.com/ultralytics/yolov5), and the [ultralytics](https://github.com/ultralytics/ultralytics/) package (from the developers of YOLOv5) has a zillion bells and whistles for both inference and fine-tuning that this package doesn't.
+If you are a computer-vision-y person looking to run or fine-tune MegaDetector programmatically, you probably don't want this package.  MegaDetector is just a fine-tuned version of [YOLOv5](https://github.com/ultralytics/yolov5), and the [ultralytics](https://github.com/ultralytics/ultralytics/) package (from the developers of YOLOv5) has a zillion bells and whistles for both inference and fine-tuning that this package doesn't.
 
 ## Reasons you might want to use this package
 
 If you want to programmatically interact with the postprocessing tools from the MegaDetector repo, or programmatically run MegaDetector in a way that produces [Timelapse](https://saul.cpsc.ucalgary.ca/timelapse)-friendly output (i.e., output in the standard [MegaDetector output format](https://github.com/agentmorris/MegaDetector/tree/main/megadetector/api/batch_processing#megadetector-batch-output-format)), this package might be for you.
 
-Although even if that describes you, you <i>still</i> might be better off cloning the MegaDetector repo.  Pip-installability requires that some dependencies be newer than what was available at the time MDv5 was trained, so results are <i>very slightly</i> different than results produced in the "official" environment.  These differences <i>probably</i> don't matter much, but they have not been formally characterized.
-
 ## If I haven't talked you out of using this package...
 
 To install:

{megadetector-5.0.15.dist-info → megadetector-5.0.17.dist-info}/RECORD

@@ -65,12 +65,12 @@ megadetector/data_management/labelme_to_yolo.py,sha256=dRePSOwU_jiCr0EakDQCz1Ct-
 megadetector/data_management/ocr_tools.py,sha256=T9ClY3B-blnK3-UF1vpVdageknYsykm_6FAfqn0kliU,32529
 megadetector/data_management/read_exif.py,sha256=-q0NqJ3VZSBovD_d6de-s3UR2NuKF6gSw2etfvVuRO4,27866
 megadetector/data_management/remap_coco_categories.py,sha256=xXWv0QhTjkUfc9RKtAZanK77HMSq_21mFg_34KFD6hw,2903
-megadetector/data_management/remove_exif.py,sha256=9YwMUliszhVzkkUcotpRKA-a3h5WdQF1taQ594Bgm60,1666
+megadetector/data_management/remove_exif.py,sha256=vIWnJfw1i9JgyQKUDGEzzqkHro4ndykIPFWhtkm6RAU,2502
 megadetector/data_management/rename_images.py,sha256=AG3YIxXEYdGmK4G-rv0_XZIylPqOZpS6gfEkydF6oDg,6918
 megadetector/data_management/resize_coco_dataset.py,sha256=AaiV7efIcNnqsXsnQckmHq2G__7ZQHBV_jN6rhZfMjo,6810
 megadetector/data_management/wi_download_csv_to_coco.py,sha256=ilnJZhNZK-FGUR-AfUSWjIDUk9Gytgxw7IOK_N8WKLE,8350
 megadetector/data_management/yolo_output_to_md_output.py,sha256=VZtatLoryeh2pbh1fRAJe-ao7vtoNn6ACyRbAk-2Mlg,17561
-megadetector/data_management/yolo_to_coco.py,sha256=G9XiB9D8PWaCq_kc61pKe2GkkuKwdJ7K7zsbGShb_jw,25176
+megadetector/data_management/yolo_to_coco.py,sha256=TzAagQ2ATbB_tn1oZxrHCWsrFGO_OhfZmi-3X45WdDU,26180
 megadetector/data_management/annotations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 megadetector/data_management/annotations/annotation_constants.py,sha256=1597MpAr_HdidIHoDFj4RgUO3K5e2Xm2bGafGeonR2k,953
 megadetector/data_management/databases/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -95,6 +95,7 @@ megadetector/data_management/importers/filenames_to_json.py,sha256=Jc_FydTiZWsB6
 megadetector/data_management/importers/helena_to_cct.py,sha256=IVTXXxDDxtbvYZaABCmnYWi2ZJ_1xpAXQG1TjOhRuVE,8712
 megadetector/data_management/importers/idaho-camera-traps.py,sha256=9BpMwygyN8OLimGsHIodNrikVgSK9SGkZJ0c10GxT-0,54112
 megadetector/data_management/importers/idfg_iwildcam_lila_prep.py,sha256=ql0fnO-IZuyT4611n8oYlTMDibhiDLDES1za1o6BEck,8194
+megadetector/data_management/importers/import_desert_lion_conservation_camera_traps.py,sha256=eILnUvSOR7upfewX_44cM8d73E9UQQxKYTkPUfIPMrY,12985
 megadetector/data_management/importers/jb_csv_to_json.py,sha256=IPoXwdz2OhrjMyK1Yv98PVmAD4VBZ9prSuXhx1xLfcg,3726
 megadetector/data_management/importers/mcgill_to_json.py,sha256=dfSxU1hHimyGT6Zt64XFrW63GWGsdKpqRrp5PE--xUw,6702
 megadetector/data_management/importers/missouri_to_json.py,sha256=C0ia3eCEZujVUKE2gmQc6ScsK8kXWM7m0ibeKgHfXNo,14848
@@ -108,7 +109,7 @@ megadetector/data_management/importers/rspb_to_json.py,sha256=y03v1d1un9mI3HZRCZ
 megadetector/data_management/importers/save_the_elephants_survey_A.py,sha256=lugw8m5Nh2Fhs-FYo9L0mDL3_29nAweLxEul6GekdkI,10669
 megadetector/data_management/importers/save_the_elephants_survey_B.py,sha256=SWClXENsIePwifP8eJeRsj3kh3Bztl6Kzc_BdqNZvFw,11172
 megadetector/data_management/importers/snapshot_safari_importer.py,sha256=dQ1GmpHcrQCQF9YZ0UaLTvc_3aOZEDqWGcxzYQeq4ho,23605
-megadetector/data_management/importers/snapshot_safari_importer_reprise.py,sha256=cv2zOWmhvXPRM-ZFrzmYFjq0Y2fwo7PUN_UJ_T2aryo,22333
+megadetector/data_management/importers/snapshot_safari_importer_reprise.py,sha256=f2WXC22fzbKaQl2888bfUlzap4oDhRG3ysZOUMBrcw0,22549
 megadetector/data_management/importers/snapshot_serengeti_lila.py,sha256=-aYq_5IxhpcR6oxFYYVv98WVnGAr0mnVkbX-oJCPd8M,33865
 megadetector/data_management/importers/sulross_get_exif.py,sha256=Bt1tGYtr5CllxCe2BL8uI3SfPu3e1SSqijnOz--iRqQ,2071
 megadetector/data_management/importers/timelapse_csv_set_to_json.py,sha256=B9VbBltf3IdPBI2O1Cmg8wODhlIML4MQpjdhTFD4GP4,15916
@@ -129,20 +130,20 @@ megadetector/data_management/lila/create_lila_blank_set.py,sha256=SBwpM0-pycW37T
 megadetector/data_management/lila/create_lila_test_set.py,sha256=DjivKgsFJlO1IHezXrwAGpiCAhLVmvPnv2nJYpv1ABU,4835
 megadetector/data_management/lila/create_links_to_md_results_files.py,sha256=MvaPBAgdwoxaNrRaKZ8mGaOCky1BYXlrT08tPG9BrpM,3803
 megadetector/data_management/lila/download_lila_subset.py,sha256=rh09kphSCVPlUGuYY-CkSyd8dy0pBUdth6uHkZ84sEo,5345
-megadetector/data_management/lila/generate_lila_per_image_labels.py,sha256=awfBLjVgwP39a2nySMZSAzcoAMHcblzYGlQVt2jP45E,18075
+megadetector/data_management/lila/generate_lila_per_image_labels.py,sha256=K54-JS7s88HsugtaXo56P22PiPsGEdHYB2AaGMBhvIY,18135
 megadetector/data_management/lila/get_lila_annotation_counts.py,sha256=aOkjemasOqf1Uixu-yhaFKYyKILYRZQZi4GBW4sbtic,5602
 megadetector/data_management/lila/get_lila_image_counts.py,sha256=UxXS5RDnSA_WbxE92qN-N7p-qR-jbyTsTZ7duLo06us,3620
 megadetector/data_management/lila/lila_common.py,sha256=IEnGoyRgcqbek1qJ1gFE83p1Pg_5kaMS-nQI25lRWIs,10132
-megadetector/data_management/lila/test_lila_metadata_urls.py,sha256=2zKNjgqC3kxdFfyvQC3KTlpc9lf2iMzecHQBf--r_Tk,4438
+megadetector/data_management/lila/test_lila_metadata_urls.py,sha256=jqN7UID16fu78BK_2sygb4s9BBeVCpSZT3_oL2GYxxY,4438
 megadetector/detection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-megadetector/detection/process_video.py,sha256=xV24TWlQ0ImN21DCPkLs7y3oUOP7cjmyrFD0PFzzhsY,42713
-megadetector/detection/pytorch_detector.py,sha256=p70kAX5pqU4SO4GjYJmzbTPV4tKUp5WRapOs7vgSKes,13885
-megadetector/detection/run_detector.py,sha256=biXbeS8aNDlidilxjzhZ-p4_wr2ID-rpsRklbNEd7ME,30094
-megadetector/detection/run_detector_batch.py,sha256=nplmaxOcEe_vnS3VrUd49uZoCQNRmJQmbSMpi8uhh8k,57064
-megadetector/detection/run_inference_with_yolov5_val.py,sha256=u9i1ndwl_k0DsiAWYQcYrrrB9D9Wt56_k6iGTAetUaM,46786
+megadetector/detection/process_video.py,sha256=yVjkm5SxHH-R5SazMQmF-XXRhrhPdE2z4X4bGkfeN-k,50019
+megadetector/detection/pytorch_detector.py,sha256=StOnaspDBkMeePiTyq5ZEcFUDBEddq36nigHXbF-zAQ,14029
+megadetector/detection/run_detector.py,sha256=vEfq3jJTseD0sIM9MaIhbeEVqP6JoLXOC2cl8Dhehxs,30553
+megadetector/detection/run_detector_batch.py,sha256=d0fayCVXzKxa1tCiw6D8kmDqcwOAIuvrgw_Zfw0eRjE,57304
+megadetector/detection/run_inference_with_yolov5_val.py,sha256=yjNm130qntOyJ4jbetdt5xDHWnSmBXRydyxB2I56XjM,49099
 megadetector/detection/run_tiled_inference.py,sha256=vw0713eNuMiEOjHfweQl58zPHNxPOMdFWZ8bTDLhlMY,37883
-megadetector/detection/tf_detector.py,sha256=-vcBuYRRLKumUj6imcDYgCgClGji0a21uMjoUAtY3yw,8104
-megadetector/detection/video_utils.py,sha256=DNEW10EgWN5ZiJg9uRpxxfJLuBX9Ts2l0eJ66F9kmmw,32474
+megadetector/detection/tf_detector.py,sha256=5V94a0gR6WmGPacKm59hl1eYEZI8cG04frF4EvHrmzU,8285
+megadetector/detection/video_utils.py,sha256=MzD8aUgdyAD9xK9w2fK0lvZtDhjpeHDkftvRXk3YJVA,41399
 megadetector/detection/detector_training/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 megadetector/detection/detector_training/model_main_tf2.py,sha256=YwNsZ7hkIFaEuwKU0rHG_VyqiR_0E01BbdlD0Yx4Smo,4936
 megadetector/postprocessing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -153,49 +154,50 @@ megadetector/postprocessing/combine_api_outputs.py,sha256=xCJHEKca8YW-mupEr0yNNw
 megadetector/postprocessing/compare_batch_results.py,sha256=7O5c6-JsIDpuIGobks_R9j8MPuiZQRnEtNnJQsJqICM,38918
 megadetector/postprocessing/convert_output_format.py,sha256=HwThfK76UPEAGa3KQbJ_tMKIrUvJ3JhKoQVWJt9dPBk,15447
 megadetector/postprocessing/load_api_results.py,sha256=FqcaiPMuqTojZOV3Jn14pJESpuwjWGbZtcvJuVXUaDM,6861
-megadetector/postprocessing/md_to_coco.py,sha256=t8zHN3QmwxuvcQKxLd_yMSjwncxy7YEoq2EGr0kwBDs,11049
+megadetector/postprocessing/md_to_coco.py,sha256=x3sUnOLd2lVfdG2zRN7k-oUvx6rvRD7DWmWJymPc108,12359
 megadetector/postprocessing/md_to_labelme.py,sha256=hejMKVxaz_xdtsGDPTQkeWuis7gzT-VOrL2Qf8ym1x0,11703
 megadetector/postprocessing/merge_detections.py,sha256=AEMgMivhph1vph_t_Qv85d9iHynT2nvq7otN4KGrDLU,17776
-megadetector/postprocessing/postprocess_batch_results.py,sha256=ucFW2WsuoxIgEC62CrgOLCOTO3LxIZ-LPCYRJ9xjais,78178
+megadetector/postprocessing/postprocess_batch_results.py,sha256=xa1FCQnzo1B6Inq8EWqS_In5xDu3qNzES_YdZ0INKr0,78978
 megadetector/postprocessing/remap_detection_categories.py,sha256=d9IYTa0i_KbbrarJc_mczABmdwypscl5-KpK8Hx_z8o,6640
 megadetector/postprocessing/render_detection_confusion_matrix.py,sha256=_wsk4W0PbNiqmFuHy-EA0Z07B1tQLMsdCTPatnHAdZw,27382
 megadetector/postprocessing/separate_detections_into_folders.py,sha256=k42gxnL8hbBiV0e2T-jmFrhxzIxnhi57Nx9cDSSL5s0,31218
-megadetector/postprocessing/subset_json_detector_output.py,sha256=TIXIWEv0nh4cXvhMLcM_ZryM5ly1NOTkWopM2RjEpqQ,26822
+megadetector/postprocessing/subset_json_detector_output.py,sha256=PDgb6cnsFm9d4E7_sMVIguLIU7s79uFQa2CRCxAO0F4,27064
 megadetector/postprocessing/top_folders_to_bottom.py,sha256=Dqk-KZXiRlIYlmLZmk6aUapmaaLJUKOf8wK1kxt9W6A,6283
 megadetector/postprocessing/repeat_detection_elimination/find_repeat_detections.py,sha256=e4Y9CyMyd-bLN3il8tu76vI0nVYHZlhZr6vcL0J4zQ0,9832
 megadetector/postprocessing/repeat_detection_elimination/remove_repeat_detections.py,sha256=tARPxuY0OyQgpKU2XqiQPko3f-hHnWuISB8ZlZgXwxI,2819
-megadetector/postprocessing/repeat_detection_elimination/repeat_detections_core.py,sha256=_RX0Gtb8YQPYdfQDGIvg1RvyqsdyanmEg1pqVmheHlg,67776
+megadetector/postprocessing/repeat_detection_elimination/repeat_detections_core.py,sha256=vEmWLSSv0_rxDwhjz_S9YaKZ_LM2tADTz2JYb_zUCnc,67923
 megadetector/taxonomy_mapping/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 megadetector/taxonomy_mapping/map_lila_taxonomy_to_wi_taxonomy.py,sha256=6D_YHTeWTs6O8S9ABog2t9-wfQSh9dW2k9XTqXUZKfo,17927
-megadetector/taxonomy_mapping/map_new_lila_datasets.py,sha256=M-hRnQuqh5QhW-7LmTvYRex1Y2izQFSgEzb92gqqx1M,4062
-megadetector/taxonomy_mapping/prepare_lila_taxonomy_release.py,sha256=N9TUgg3_2u4hc5OBRydvEpweC3RIJ9ry5bXoi1BXLAY,4676
-megadetector/taxonomy_mapping/preview_lila_taxonomy.py,sha256=3e-e3rurissksHgRCrc-_oLJSy2KCxcvwtAQM7L2E1U,19549
+megadetector/taxonomy_mapping/map_new_lila_datasets.py,sha256=FSJ6ygpADtlYLf5Bhp9kMb5km2-MH0mmM_ccyStxo34,4054
+megadetector/taxonomy_mapping/prepare_lila_taxonomy_release.py,sha256=sRCTgaY84FiGoTtK5LOHL5dhpSrEk9zZGkUR1w9FNm4,4694
+megadetector/taxonomy_mapping/preview_lila_taxonomy.py,sha256=qCOyhrgddFZOYBCamfIDKdMMQuIMdGhSrd7ovLz1Yuo,19549
 megadetector/taxonomy_mapping/retrieve_sample_image.py,sha256=4cfWsLRwS_EwAmQr2p5tA_W6glBK71tSjPfaHxUZQWs,1979
-megadetector/taxonomy_mapping/simple_image_download.py,sha256=_1dEGn4356mdQAy9yzkH5DntPO7-nQyYo2zm08ODpJc,6852
-megadetector/taxonomy_mapping/species_lookup.py,sha256=B5arfF1OVICtTokVOtJcN8W2SxGmq46AO0SfA11Upt8,28291
+megadetector/taxonomy_mapping/simple_image_download.py,sha256=wLhyMSocX_JhDGA6yLbEfpysz8MMI8YFJWaxyA-GZ9c,6932
+megadetector/taxonomy_mapping/species_lookup.py,sha256=HZ7fyhap9CNdhdmq-id8dMnIa9TPMA3557rsamAkWkU,28329
 megadetector/taxonomy_mapping/taxonomy_csv_checker.py,sha256=A_zPwzY-ERz6xawxgk2Tpfsycl-1sDcjUiuaXXBppi8,4850
 megadetector/taxonomy_mapping/taxonomy_graph.py,sha256=ayrTFseVaIMbtMXhnjWCkZdxI5SAVe_BUtnanGewQpU,12263
 megadetector/taxonomy_mapping/validate_lila_category_mappings.py,sha256=1qyZr23bvZSVUYLQnO1XAtIZ4jdpARA5dxt8euKVyOA,2527
 megadetector/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 megadetector/utils/azure_utils.py,sha256=0BdnkG2hW-X0yFpsJqmBhOd2wysz_LvhuyImPJMVPJs,6271
-megadetector/utils/ct_utils.py,sha256=RTMc0UszYuW9QpMo-qetaWder1mFWIzkMLL2UM6PYdY,17960
+megadetector/utils/ct_utils.py,sha256=1LXAjnzeeFeQqp59cWn3Nxt5OQk3t2DfO5wQ30flA5E,19441
 megadetector/utils/directory_listing.py,sha256=r4rg2xA4O9ZVxVtzPZzXIXa0DOEukAJMTTNcNSiQcuM,9668
-megadetector/utils/md_tests.py,sha256=mtjxQ_dQYBgo8OOVta5JrPhuDMT1ZNh0S-OQXRocBEM,51236
-megadetector/utils/path_utils.py,sha256=Uj_aNvA_P0buq-3ebQLZz-6to8mNO5JyBhD7n1-pUoU,37149
+megadetector/utils/md_tests.py,sha256=n_5PkeUComn8pbvN-sLS4XdNsNPnvz8jk6DhrCcm9PU,58225
+megadetector/utils/path_utils.py,sha256=o68jfPDaLj3NizipVCQEnmB5GfPHpMOLUmQWamYM4w0,37165
 megadetector/utils/process_utils.py,sha256=2SdFVxqob-YUW2BTjUEavNuRH3jA4V05fbKMtrVSd3c,5635
 megadetector/utils/sas_blob_utils.py,sha256=k76EcMmJc_otrEHcfV2fxAC6fNhxU88FxM3ddSYrsKU,16917
 megadetector/utils/split_locations_into_train_val.py,sha256=jvaDu1xKB51L3Xq2nXQo0XtXRjNRf8RglBApl1g6gHo,10101
 megadetector/utils/string_utils.py,sha256=ZQapJodzvTDyQhjZgMoMl3-9bqnKAUlORpws8Db9AkA,2050
-megadetector/utils/url_utils.py,sha256=uJRsSMxA1zMd997dX3V3wqFnKMTcSiOaE_atXUTRRVI,11476
+megadetector/utils/torch_test.py,sha256=aEYE-1vGt5PujD0bHAVRTJiLrKFlGWpS8zeYhqEYZLY,853
+megadetector/utils/url_utils.py,sha256=yybWwJ-vl2A6Fci66i-xt_dl3Uqh72Ylnb8XOT2Grog,14835
 megadetector/utils/write_html_image_list.py,sha256=apzoWkgZWG-ybCT4k92PlS4-guN_sNBSMMMbj7Cfm1k,8638
 megadetector/visualization/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 megadetector/visualization/plot_utils.py,sha256=lOfU3uPrcuHZagV_1SN8erT8PujIepocgw6KZ17Ej6c,10671
 megadetector/visualization/render_images_with_thumbnails.py,sha256=kgJYW8BsqRO4C7T3sqItdBuSkZ64I1vOtIWAsVG4XBI,10589
-megadetector/visualization/visualization_utils.py,sha256=jWiXlLpmWh_CH2vApZURclOC7fdip1aKWQ66wuNabyA,62369
-megadetector/visualization/visualize_db.py,sha256=3FhOtn3GHvNsomwSpsSEzYe58lF9B4Ob3MEi_xplrdo,21256
+megadetector/visualization/visualization_utils.py,sha256=J53VsI8aQmzzBBeu-msm8c-qC6pm_HCMkMKYvnylqjo,63083
+megadetector/visualization/visualize_db.py,sha256=x9jScwG-3V-mZGy5cB1s85KWbiAIfvgVUcLqUplHxGA,22110
 megadetector/visualization/visualize_detector_output.py,sha256=LY8QgDWpWlXVLZJUskvT29CdkNvIlEsFTk4DC_lS6pk,17052
-megadetector-5.0.15.dist-info/LICENSE,sha256=RMa3qq-7Cyk7DdtqRj_bP1oInGFgjyHn9-PZ3PcrqIs,1100
-megadetector-5.0.15.dist-info/METADATA,sha256=E3ZvrTIEHvAVmogrd9wXYmYgvHBo9YsFmIb6-I9uEb0,7893
-megadetector-5.0.15.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-megadetector-5.0.15.dist-info/top_level.txt,sha256=wf9DXa8EwiOSZ4G5IPjakSxBPxTDjhYYnqWRfR-zS4M,13
-megadetector-5.0.15.dist-info/RECORD,,
+megadetector-5.0.17.dist-info/LICENSE,sha256=RMa3qq-7Cyk7DdtqRj_bP1oInGFgjyHn9-PZ3PcrqIs,1100
+megadetector-5.0.17.dist-info/METADATA,sha256=gGtsuo3rHyxfYxhvxEDnP9RZfFKL2_jDvuIR51KlwqQ,7460
+megadetector-5.0.17.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
+megadetector-5.0.17.dist-info/top_level.txt,sha256=wf9DXa8EwiOSZ4G5IPjakSxBPxTDjhYYnqWRfR-zS4M,13
+megadetector-5.0.17.dist-info/RECORD,,

{megadetector-5.0.15.dist-info → megadetector-5.0.17.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: setuptools (74.1.2)
 Root-Is-Purelib: true
 Tag: py3-none-any