handle image absence

datumaro/datumaro/cli/contexts/project/__init__.py

@@ -650,13 +650,14 @@ def stats_command(args):
  project = load_project(args.project_dir)
 
  dataset = project.make_dataset()
- stats = compute_image_statistics(dataset)
+ stats = {}
+ stats.update(compute_image_statistics(dataset))
  stats.update(compute_ann_statistics(dataset))
 
  dst_file = generate_next_file_name('statistics', ext='.json')
  log.info("Writing project statistics to '%s'" % dst_file)
  with open(dst_file, 'w') as f:
- json.dump(stats, f)
+ json.dump(stats, f, indent=4, sort_keys=True)
 
 def build_info_parser(parser_ctor=argparse.ArgumentParser):
  parser = parser_ctor(help="Get project info",

datumaro/datumaro/components/operations.py

@@ -3,6 +3,7 @@
 #
 # SPDX-License-Identifier: MIT
 
+import logging as log
 from copy import deepcopy
 
 import cv2
@@ -94,13 +95,31 @@ def compute_image_statistics(dataset):
  }
 
  def _extractor_stats(extractor):
- mean, std = mean_std(extractor)
- return {
+ available = True
+ for item in extractor:
+ if not (item.has_image and item.image.has_data):
+ available = False
+ log.warn("Item %s has no image. Image stats won't be computed",
+ item.id)
+ break
+
+ stats = {
  'images count': len(extractor),
- 'image mean': [float(n) for n in mean[::-1]],
- 'image std': [float(n) for n in std[::-1]],
  }
 
+ if available:
+ mean, std = mean_std(extractor)
+ stats.update({
+ 'image mean': [float(n) for n in mean[::-1]],
+ 'image std': [float(n) for n in std[::-1]],
+ })
+ else:
+ stats.update({
+ 'image mean': 'n/a',
+ 'image std': 'n/a',
+ })
+ return stats
+
  stats['dataset'].update(_extractor_stats(dataset))
 
  subsets = dataset.subsets() or [None]