megadetector 5.0.21__py3-none-any.whl → 5.0.22__py3-none-any.whl

megadetector/postprocessing/validate_batch_results.py

@@ -15,8 +15,10 @@ import sys
 import json
 import argparse
 
+from tqdm import tqdm
+
 from megadetector.detection.video_utils import is_video_file
-from megadetector.utils.ct_utils import args_to_object
+from megadetector.utils.ct_utils import args_to_object, is_list_sorted # noqa
 
 typical_info_fields = ['detector','detection_completion_time',
                        'classifier','classification_completion_time',
@@ -45,6 +47,9 @@ class ValidateBatchResultsOptions:
         
         #: Should we return the loaded data, or just the validation results?
         self.return_data = False
+        
+        #: Enable additional debug output
+        self.verbose = False
     
 # ...class ValidateBatchResultsOptions
 
@@ -73,6 +78,9 @@ def validate_batch_results(json_filename,options=None):
     if options is None:
         options = ValidateBatchResultsOptions()
     
+    if options.verbose:
+        print('Loading results from {}'.format(json_filename))
+        
     with open(json_filename,'r') as f:
         d = json.load(f)
     
@@ -140,8 +148,11 @@ def validate_batch_results(json_filename,options=None):
         if not isinstance(d['images'],list):
             raise ValueError('Invalid images field')
         
+        if options.verbose:
+            print('Validating images')
+            
         # im = d['images'][0]
-        for i_im,im in enumerate(d['images']):
+        for i_im,im in tqdm(enumerate(d['images']),total=len(d['images']),disable=(not options.verbose)):
             
             if not isinstance(im,dict):
                 raise ValueError('Invalid image at index {}'.format(i_im))
@@ -150,34 +161,61 @@ def validate_batch_results(json_filename,options=None):
             
             file = im['file']
             
+            if 'detections' in im and im['detections'] is not None:
+                for det in im['detections']:
+                    assert 'category' in det, 'Image {} has a detection with no category'.format(file)
+                    assert 'conf' in det, 'Image {} has a detection with no confidence'.format(file)
+                    assert isinstance(det['conf'],float), \
+                        'Image {} has an illegal confidence value'.format(file)
+                    assert 'bbox' in det, 'Image {} has a detection with no box'.format(file)
+                    assert det['category'] in d['detection_categories'], \
+                        'Image {} has a detection with an unmapped category {}'.format(
+                            file,det['category'])                    
+                
             if options.check_image_existence:
+                
                 if options.relative_path_base is None:
                     file_abs = file
                 else:
                     file_abs = os.path.join(options.relative_path_base,file)
                 if not os.path.isfile(file_abs):
                     raise ValueError('Cannot find file {}'.format(file_abs))
-                
-            if ('detections' not in im) or (im['detections'] is None):
-                if not ('failure' in im and isinstance(im['failure'],str)):
-                    raise ValueError('Image {} has no detections and no failure'.format(im['file']))
+            
+            if 'failure' in im:
+                if im['failure'] is not None:
+                    if not isinstance(im['failure'],str):
+                        raise ValueError('Image {} has an illegal [failure] value: {}'.format(
+                            im['file'],str(im['failure'])))
+                    if 'detections' not in im:
+                        s = 'Image {} has a failure value, should also have a null detections array'.format(
+                            im['file'])
+                        validation_results['warnings'].append(s)
+                    elif im['detections'] is not None:
+                        raise ValueError('Image {} has a failure value but a non-null detections array'.format(
+                            im['file']))
             else:
                 if not isinstance(im['detections'],list):
                     raise ValueError('Invalid detections list for image {}'.format(im['file']))
-                
+              
             if is_video_file(im['file']) and (format_version >= 1.4):
+                
                 if 'frame_rate' not in im:
                     raise ValueError('Video without frame rate: {}'.format(im['file']))
+                if im['frame_rate'] < 0:
+                    raise ValueError('Video with illegal frame rate {}: {}'.format(
+                        str(im['frame_rate']),im['file']))
                 if 'detections' in im and im['detections'] is not None:
                     for det in im['detections']:
                         if 'frame_number' not in det:
                             raise ValueError('Frame without frame number in video {}'.format(
                                 im['file']))
+                    frame_numbers = [det['frame_number'] for det in im['detections']] # noqa
+                    # assert is_list_sorted(frame_numbers)                    
                 
         # ...for each image
             
         
-        ## Checking on other keys
+        ## Validation of other keys
         
         for k in d.keys():                        
             if (k not in typical_keys) and (k not in required_keys):
@@ -188,6 +226,8 @@ def validate_batch_results(json_filename,options=None):
         
         validation_results['errors'].append(str(e))
         
+    # ...try/except
+    
     if options.return_data:
         to_return = d
     else:
@@ -204,15 +244,25 @@ def validate_batch_results(json_filename,options=None):
 
 if False:
 
-    #%%
+    #%% Validate all .json files in the MD test suite
+    
+    from megadetector.utils.path_utils import recursive_file_list
+    filenames = recursive_file_list(os.path.expanduser('~/AppData/Local/Temp/md-tests'))
+    filenames = [fn for fn in filenames if fn.endswith('.json')]
+    filenames = [fn for fn in filenames if 'detectionIndex' not in fn]
     
     options = ValidateBatchResultsOptions()
-    # json_filename = r'g:\temp\format.json'
-    # json_filename = r'g:\temp\test-videos\video_results.json'
-    json_filename = r'g:\temp\test-videos\image_results.json'
-    options.check_image_existence = True
-    options.relative_path_base = r'g:\temp\test-videos'
-    validate_batch_results(json_filename,options)
+    options.check_image_existence = False
+    options.relative_path_base = None # r'g:\temp\test-videos'
+    
+    for json_filename in filenames:
+        results = validate_batch_results(json_filename,options)
+        if len(results['validation_results']['warnings']) > 0:
+            print('Warnings in file {}:'.format(json_filename))
+            for s in results['validation_results']['warnings']:
+                print(s)
+            print('')
+        assert len(results['validation_results']['errors']) == 0    
     
 
 #%% Command-line driver

megadetector/taxonomy_mapping/map_new_lila_datasets.py

@@ -15,15 +15,17 @@ import json
 # Created by get_lila_category_list.py
 input_lila_category_list_file = os.path.expanduser('~/lila/lila_categories_list/lila_dataset_to_categories.json')
 
-output_file = os.path.expanduser('~/lila/lila_additions_2024.10.05.csv')
+output_file = os.path.expanduser('~/lila/lila_additions_2024.12.31.csv')
 
 datasets_to_map = [
-    'Ohio Small Animals'
+    'Seattle(ish) Camera Traps'
     ]
 
 
 #%% Initialize taxonomic lookup
 
+# Takes ~2 mins
+
 from megadetector.taxonomy_mapping.species_lookup import \
     initialize_taxonomy_lookup, get_preferred_taxonomic_match
 
@@ -39,27 +41,27 @@ lila_datasets = set()
 
 for dataset_name in input_lila_categories.keys():
     # The script that generates this dictionary creates a separate entry for bounding box
-    # metadata files, but those don't represent new dataset names
+    # metadata files, but those don't represent new dataset names, so we ignore them here.
     lila_datasets.add(dataset_name.replace('_bbox',''))
-    
+
 for s in datasets_to_map:
     assert s in lila_datasets
-    
-    
+
+
 #%% Find all categories    
 
 category_mappings = []
 
 # dataset_name = datasets_to_map[0]
 for dataset_name in datasets_to_map:
-    
+
     ds_categories = input_lila_categories[dataset_name]
     for category in ds_categories:
         category_name = category['name']
         assert ':' not in category_name
         mapping_name = dataset_name + ':' + category_name
         category_mappings.append(mapping_name)
-        
+
 print('Need to create {} mappings'.format(len(category_mappings)))
 
 
@@ -128,22 +130,23 @@ output_df.to_csv(output_file, index=None, header=True)
 
 if False:
 
-    #%%
-
+    #%% You probably want to open the .csv file first
+    
     from megadetector.utils.path_utils import open_file
     open_file(output_file)
+
     
     #%%
     
     # q = 'white-throated monkey'
     # q = 'cingulata'
     # q = 'notamacropus'
-    q = 'thamnophis saurita saurita'
+    q = 'insects'
     taxonomy_preference = 'inat'
     m = get_preferred_taxonomic_match(q,taxonomy_preference)
     # print(m.scientific_name); import clipboard; clipboard.copy(m.scientific_name)
     
-    if m is None:
+    if (m is None) or (len(m.taxonomy_string) == 0):
         print('No match')
     else:
         if m.source != taxonomy_preference:

megadetector/taxonomy_mapping/prepare_lila_taxonomy_release.py

@@ -89,7 +89,7 @@ if False:
                         'genus',
                         'species','subspecies','variety']
 
-    levels_to_exclude = ['stateofmatter','zoosection','parvorder','complex']
+    levels_to_exclude = ['stateofmatter','zoosection','parvorder','complex','epifamily']
 
     for s in levels_to_exclude:
         assert s not in levels_to_include

megadetector/taxonomy_mapping/preview_lila_taxonomy.py

@@ -16,7 +16,7 @@ import os
 import pandas as pd
 
 # lila_taxonomy_file = r"c:\git\agentmorrisprivate\lila-taxonomy\lila-taxonomy-mapping.csv"
-lila_taxonomy_file = os.path.expanduser('~/lila/lila_additions_2024.10.05.csv')
+lila_taxonomy_file = os.path.expanduser('~/lila/lila_additions_2024.12.31.csv')
 
 preview_base = os.path.expanduser('~/lila/lila_taxonomy_preview')
 os.makedirs(preview_base,exist_ok=True)
@@ -399,6 +399,8 @@ images_per_query = 15
 min_valid_images_per_query = 3
 min_valid_image_size = 3000
 
+# TODO: parallelize this loop
+#
 # i_row = 0; row = df.iloc[i_row]
 for i_row,row in df.iterrows():
     

megadetector/utils/ct_utils.py

@@ -12,6 +12,7 @@ import inspect
 import json
 import math
 import os
+import builtins
 
 import jsonpickle
 import numpy as np
@@ -613,6 +614,50 @@ def is_empty(v):
     return False
 
 
+def min_none(a,b):
+    """
+    Returns the minimum of a and b.  If both are None, returns None.  If one is None, 
+    returns the other.
+    
+    Args:
+        a (numeric): the first value to compare
+        b (numeric): the second value to compare
+        
+    Returns:
+        numeric: the minimum of a and b, or None
+    """
+    if a is None and b is None:
+        return None
+    elif a is None:
+        return b
+    elif b is None:
+        return a
+    else:
+        return min(a,b)
+    
+
+def max_none(a,b):
+    """
+    Returns the maximum of a and b.  If both are None, returns None.  If one is None, 
+    returns the other.
+    
+    Args:
+        a (numeric): the first value to compare
+        b (numeric): the second value to compare
+        
+    Returns:
+        numeric: the maximum of a and b, or None
+    """
+    if a is None and b is None:
+        return None
+    elif a is None:
+        return b
+    elif b is None:
+        return a
+    else:
+        return max(a,b)
+
+    
 def isnan(v):
     """
     Returns True if v is a nan-valued float, otherwise returns False.
@@ -645,7 +690,24 @@ def sets_overlap(set1, set2):
     return not set(set1).isdisjoint(set(set2))
 
 
-
+def is_function_name(s,calling_namespace):
+    """
+    Determines whether [s] is a callable function in the global or local scope, or a 
+    built-in function.
+    
+    Args:
+        s (str): the string to test for function-ness
+        calling_namespace (dict): typically pass the output of locals()
+    """
+    
+    assert isinstance(s,str), 'Input is not a string'
+    
+    return callable(globals().get(s)) or \
+        callable(locals().get(s)) or \
+        callable(calling_namespace.get(s)) or \
+        callable(getattr(builtins, s, None))
+        
+        
 #%% Test drivers
 
 if False:
@@ -678,4 +740,4 @@ if False:
     L = [{'a':5},{'a':0},{'a':10}]
     k = 'a'
     sort_list_of_dicts_by_key(L, k, reverse=True)
-    
+    

megadetector/utils/md_tests.py

@@ -1210,7 +1210,7 @@ def run_cli_tests(options):
         cmd += ' --overwrite_handling overwrite'
         cmd_results = execute_and_print(cmd)
         
-        # Run again with checkpointing, make sure the output are identical
+        # Run again with checkpointing, make sure the outputs are identical
         cmd += ' --checkpoint_frequency 5'
         inference_output_file_yolo_val_checkpoint = \
             os.path.join(options.scratch_dir,'folder_inference_output_yolo_val_checkpoint.json')

megadetector/utils/path_utils.py

@@ -32,6 +32,8 @@ from functools import partial
 from shutil import which
 from tqdm import tqdm
 
+from megadetector.utils.ct_utils import is_iterable
+
 # Should all be lower-case
 IMG_EXTENSIONS = ('.jpg', '.jpeg', '.gif', '.png', '.tif', '.tiff', '.bmp')
 
@@ -770,16 +772,21 @@ def parallel_get_file_sizes(filenames,
     
     folder_name = None
     
-    if verbose:
-        print('Enumerating files')
-        
-    if isinstance(filenames,str) and os.path.isdir(filenames):
-        
+    if isinstance(filenames,str):
+                
         folder_name = filenames
+        assert os.path.isdir(filenames), 'Could not find folder {}'.format(folder_name)        
         
+        if verbose:
+            print('Enumerating files in {}'.format(folder_name))
+                    
         # Enumerate absolute paths here, we'll convert to relative later if requested
-        filenames = recursive_file_list(filenames,recursive=recursive,return_relative_paths=False)
+        filenames = recursive_file_list(folder_name,recursive=recursive,return_relative_paths=False)
 
+    else:
+        
+        assert is_iterable(filenames), '[filenames] argument is neither a folder nor an iterable'
+    
     if verbose:
         print('Creating worker pool')
     
@@ -940,7 +947,7 @@ def zip_folder(input_folder, output_fn=None, overwrite=False, verbose=False, com
         output_fn (str, optional): output filename; if this is None, we'll write to [input_folder].zip
         overwrite (bool, optional): whether to overwrite an existing .tar file
         verbose (bool, optional): enable additional debug console output
-        compresslevel (int, optional): compression level to use, between 0 and 9
+        compresslevel (int, optional): compression level to use, between 0 and 9        
         
     Returns:
         str: the output zipfile, whether we created it or determined that it already exists    

megadetector/utils/process_utils.py

@@ -59,8 +59,13 @@ def execute(cmd,encoding=None,errors=None,env=None,verbose=False):
     return return_code
 
 
-def execute_and_print(cmd,print_output=True,encoding=None,errors=None,
-                      env=None,verbose=False,catch_exceptions=True,
+def execute_and_print(cmd,
+                      print_output=True,
+                      encoding=None,
+                      errors=None,
+                      env=None,
+                      verbose=False,
+                      catch_exceptions=True,
                       echo_command=False):
     """
     Run [cmd] (a single string) in a shell, capturing and printing output.  Returns
@@ -73,7 +78,8 @@ def execute_and_print(cmd,print_output=True,encoding=None,errors=None,
     
     Args:
         cmd (str): command to run
-        print_output (bool, optional): whether to print output from [cmd]
+        print_output (bool, optional): whether to print output from [cmd] (stdout is 
+            captured regardless of the value of print_output)
         encoding (str, optional): stdout encoding, see Popen() documentation
         errors (str, optional): error handling, see Popen() documentation
         env (dict, optional): environment variables, see Popen() documentation

megadetector/utils/write_html_image_list.py

@@ -44,6 +44,7 @@ def write_html_image_list(filename=None,images=None,options=None):
             - fHtml (file pointer to write to, used for splitting write operations over multiple calls)
             - pageTitle (HTML page title)
             - headerHtml (html text to include before the image list)
+            - subPageHeaderHtml (html text to include before the images when images are broken into pages)
             - trailerHtml (html text to include after the image list)
             - defaultImageStyle (default css style for images)
             - defaultTextStyle (default css style for image titles)
@@ -67,6 +68,9 @@ def write_html_image_list(filename=None,images=None,options=None):
     if 'headerHtml' not in options or options['headerHtml'] is None:
         options['headerHtml'] = ''
     
+    if 'subPageHeaderHtml' not in options or options['subPageHeaderHtml'] is None:
+        options['subPageHeaderHtml'] = ''
+        
     if 'trailerHtml' not in options or options['trailerHtml'] is None:
         options['trailerHtml'] = ''
     
@@ -152,7 +156,7 @@ def write_html_image_list(filename=None,images=None,options=None):
             localImages = images[iStart:iEnd+1]
             
             localOptions = options.copy();
-            localOptions['headerHtml'] = '';
+            localOptions['headerHtml'] = options['subPageHeaderHtml'];
             localOptions['trailerHtml'] = '';
             
             # Make a recursive call for this image set