[Datumaro] Add dataset statistics

CHANGELOG.md

@@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 - Siammask tracker as DL serverless function (<https://github.com/opencv/cvat/pull/1988>)
 - [Datumaro] Added model info and source info commands (<https://github.com/opencv/cvat/pull/1973>)
+- [Datumaro] Dataset statistics (<https://github.com/opencv/cvat/pull/1668>)
 
 ### Changed
 - Shape coordinates are rounded to 2 digits in dumped annotations (<https://github.com/opencv/cvat/pull/1970>)

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

@@ -17,7 +17,8 @@
 from datumaro.components.dataset_filter import DatasetItemEncoder
 from datumaro.components.extractor import AnnotationType
 from datumaro.components.cli_plugin import CliPlugin
-from datumaro.components.operations import mean_std
+from datumaro.components.operations import \
+ compute_image_statistics, compute_ann_statistics
 from .diff import DiffVisualizer
 from ...util import add_subparser, CliException, MultilineFormatter, \
  make_file_name
@@ -648,22 +649,16 @@ def build_stats_parser(parser_ctor=argparse.ArgumentParser):
 
 def stats_command(args):
  project = load_project(args.project_dir)
- dataset = project.make_dataset()
 
- def print_extractor_info(extractor, indent=''):
- mean, std = mean_std(dataset)
- print("%sImage mean:" % indent, ', '.join('%.3f' % n for n in mean))
- print("%sImage std:" % indent, ', '.join('%.3f' % n for n in std))
-
- print("Dataset: ")
- print_extractor_info(dataset)
-
- if 1 < len(dataset.subsets()):
- print("Subsets: ")
- for subset_name in dataset.subsets():
- subset = dataset.get_subset(subset_name)
- print(" %s:" % subset_name)
- print_extractor_info(subset, " " * 4)
+ dataset = project.make_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, 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

@@ -3,9 +3,14 @@
 #
 # SPDX-License-Identifier: MIT
 
+import logging as log
+from copy import deepcopy
+
 import cv2
 import numpy as np
 
+from datumaro.components.extractor import AnnotationType
+
 
 def mean_std(dataset):
  """
@@ -14,6 +19,8 @@ def mean_std(dataset):
  # Use an online algorithm to:
  # - handle different image sizes
  # - avoid cancellation problem
+ if len(dataset) == 0:
+ return [0, 0, 0], [0, 0, 0]
 
  stats = np.empty((len(dataset), 2, 3), dtype=np.double)
  counts = np.empty(len(dataset), dtype=np.uint32)
@@ -80,3 +87,151 @@ def compute_stats(stats, counts, mean_accessor, variance_accessor):
  *__class__.compute_stats(stats[:h], counts[:h], m, v),
  *__class__.compute_stats(stats[h:], counts[h:], m, v)
  )
+
+def compute_image_statistics(dataset):
+ stats = {
+ 'dataset': {},
+ 'subsets': {}
+ }
+
+ def _extractor_stats(extractor):
+ 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),
+ }
+
+ 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]
+ if subsets and 0 < len([s for s in subsets if s]):
+ for subset_name in subsets:
+ stats['subsets'][subset_name] = _extractor_stats(
+ dataset.get_subset(subset_name))
+
+ return stats
+
+def compute_ann_statistics(dataset):
+ labels = dataset.categories().get(AnnotationType.label)
+ def get_label(ann):
+ return labels.items[ann.label].name if ann.label is not None else None
+
+ stats = {
+ 'images count': len(dataset),
+ 'annotations count': 0,
+ 'unannotated images count': 0,
+ 'unannotated images': [],
+ 'annotations by type': { t.name: {
+ 'count': 0,
+ } for t in AnnotationType },
+ 'annotations': {},
+ }
+ by_type = stats['annotations by type']
+
+ attr_template = {
+ 'count': 0,
+ 'values count': 0,
+ 'values present': set(),
+ 'distribution': {}, # value -> (count, total%)
+ }
+ label_stat = {
+ 'count': 0,
+ 'distribution': { l.name: [0, 0] for l in labels.items
+ }, # label -> (count, total%)
+
+ 'attributes': {},
+ }
+ stats['annotations']['labels'] = label_stat
+ segm_stat = {
+ 'avg. area': 0,
+ 'area distribution': [], # a histogram with 10 bins
+ # (min, min+10%), ..., (min+90%, max) -> (count, total%)
+
+ 'pixel distribution': { l.name: [0, 0] for l in labels.items
+ }, # label -> (count, total%)
+ }
+ stats['annotations']['segments'] = segm_stat
+ segm_areas = []
+ pixel_dist = segm_stat['pixel distribution']
+ total_pixels = 0
+
+ for item in dataset:
+ if len(item.annotations) == 0:
+ stats['unannotated images'].append(item.id)
+ continue
+
+ for ann in item.annotations:
+ by_type[ann.type.name]['count'] += 1
+
+ if not hasattr(ann, 'label') or ann.label is None:
+ continue
+
+ if ann.type in {AnnotationType.mask,
+ AnnotationType.polygon, AnnotationType.bbox}:
+ area = ann.get_area()
+ segm_areas.append(area)
+ pixel_dist[get_label(ann)][0] += int(area)
+
+ label_stat['count'] += 1
+ label_stat['distribution'][get_label(ann)][0] += 1
+
+ for name, value in ann.attributes.items():
+ if name.lower() in { 'occluded', 'visibility', 'score',
+ 'id', 'track_id' }:
+ continue
+ attrs_stat = label_stat['attributes'].setdefault(name,
+ deepcopy(attr_template))
+ attrs_stat['count'] += 1
+ attrs_stat['values present'].add(str(value))
+ attrs_stat['distribution'] \
+ .setdefault(str(value), [0, 0])[0] += 1
+
+ stats['annotations count'] = sum(t['count'] for t in
+ stats['annotations by type'].values())
+ stats['unannotated images count'] = len(stats['unannotated images'])
+
+ for label_info in label_stat['distribution'].values():
+ label_info[1] = label_info[0] / label_stat['count']
+
+ for label_attr in label_stat['attributes'].values():
+ label_attr['values count'] = len(label_attr['values present'])
+ label_attr['values present'] = sorted(label_attr['values present'])
+ for attr_info in label_attr['distribution'].values():
+ attr_info[1] = attr_info[0] / label_attr['count']
+
+ # numpy.sum might be faster, but could overflow with large datasets.
+ # Python's int can transparently mutate to be of indefinite precision (long)
+ total_pixels = sum(int(a) for a in segm_areas)
+
+ segm_stat['avg. area'] = total_pixels / (len(segm_areas) or 1.0)
+
+ for label_info in segm_stat['pixel distribution'].values():
+ label_info[1] = label_info[0] / total_pixels
+
+ if len(segm_areas) != 0:
+ hist, bins = np.histogram(segm_areas)
+ segm_stat['area distribution'] = [{
+ 'min': float(bin_min), 'max': float(bin_max),
+ 'count': int(c), 'percent': int(c) / len(segm_areas)
+ } for c, (bin_min, bin_max) in zip(hist, zip(bins[:-1], bins[1:]))]
+
+ return stats

datumaro/tests/test_ops.py

@@ -1,7 +1,9 @@
 import numpy as np
 
-from datumaro.components.extractor import Extractor, DatasetItem
-from datumaro.components.operations import mean_std
+from datumaro.components.extractor import (Extractor, DatasetItem, Label,
+ Mask, Bbox, Points, Caption)
+from datumaro.components.project import Dataset
+from datumaro.components.operations import mean_std, compute_ann_statistics
 
 from unittest import TestCase
 
@@ -28,4 +30,105 @@ def __iter__(self):
  for em, am in zip(expected_mean, actual_mean):
  self.assertAlmostEqual(em, am, places=0)
  for estd, astd in zip(expected_std, actual_std):
- self.assertAlmostEqual(estd, astd, places=0)
+ self.assertAlmostEqual(estd, astd, places=0)
+
+ def test_stats(self):
+ dataset = Dataset.from_iterable([
+ DatasetItem(id=1, image=np.ones((5, 5, 3)), annotations=[
+ Caption('hello'),
+ Caption('world'),
+ Label(2, attributes={ 'x': 1, 'y': '2', }),
+ Bbox(1, 2, 2, 2, label=2, attributes={ 'score': 0.5, }),
+ Bbox(5, 6, 2, 2, attributes={
+ 'x': 1, 'y': '3', 'occluded': True,
+ }),
+ Points([1, 2, 2, 0, 1, 1], label=0),
+ Mask(label=3, image=np.array([
+ [0, 0, 1, 1, 1],
+ [0, 0, 1, 1, 1],
+ [0, 0, 1, 1, 1],
+ [0, 0, 0, 0, 0],
+ [0, 0, 0, 0, 0],
+ ])),
+ ]),
+ DatasetItem(id=2, image=np.ones((2, 4, 3)), annotations=[
+ Label(2, attributes={ 'x': 2, 'y': '2', }),
+ Bbox(1, 2, 2, 2, label=3, attributes={ 'score': 0.5, }),
+ Bbox(5, 6, 2, 2, attributes={
+ 'x': 2, 'y': '3', 'occluded': False,
+ }),
+ ]),
+ DatasetItem(id=3),
+ ], categories=['label_%s' % i for i in range(4)])
+
+ expected = {
+ 'images count': 3,
+ 'annotations count': 10,
+ 'unannotated images count': 1,
+ 'unannotated images': ['3'],
+ 'annotations by type': {
+ 'label': { 'count': 2, },
+ 'polygon': { 'count': 0, },
+ 'polyline': { 'count': 0, },
+ 'bbox': { 'count': 4, },
+ 'mask': { 'count': 1, },
+ 'points': { 'count': 1, },
+ 'caption': { 'count': 2, },
+ },
+ 'annotations': {
+ 'labels': {
+ 'count': 6,
+ 'distribution': {
+ 'label_0': [1, 1/6],
+ 'label_1': [0, 0.0],
+ 'label_2': [3, 3/6],
+ 'label_3': [2, 2/6],
+ },
+ 'attributes': {
+ 'x': {
+ 'count': 2, # unnotations with no label are skipped
+ 'values count': 2,
+ 'values present': ['1', '2'],
+ 'distribution': {
+ '1': [1, 1/2],
+ '2': [1, 1/2],
+ },
+ },
+ 'y': {
+ 'count': 2, # unnotations with no label are skipped
+ 'values count': 1,
+ 'values present': ['2'],
+ 'distribution': {
+ '2': [2, 2/2],
+ },
+ },
+ # must not include "special" attributes like "occluded"
+ }
+ },
+ 'segments': {
+ 'avg. area': (4 * 2 + 9 * 1) / 3,
+ 'area distribution': [
+ {'min': 4.0, 'max': 4.5, 'count': 2, 'percent': 2/3},
+ {'min': 4.5, 'max': 5.0, 'count': 0, 'percent': 0.0},
+ {'min': 5.0, 'max': 5.5, 'count': 0, 'percent': 0.0},
+ {'min': 5.5, 'max': 6.0, 'count': 0, 'percent': 0.0},
+ {'min': 6.0, 'max': 6.5, 'count': 0, 'percent': 0.0},
+ {'min': 6.5, 'max': 7.0, 'count': 0, 'percent': 0.0},
+ {'min': 7.0, 'max': 7.5, 'count': 0, 'percent': 0.0},
+ {'min': 7.5, 'max': 8.0, 'count': 0, 'percent': 0.0},
+ {'min': 8.0, 'max': 8.5, 'count': 0, 'percent': 0.0},
+ {'min': 8.5, 'max': 9.0, 'count': 1, 'percent': 1/3},
+ ],
+ 'pixel distribution': {
+ 'label_0': [0, 0.0],
+ 'label_1': [0, 0.0],
+ 'label_2': [4, 4/17],
+ 'label_3': [13, 13/17],
+ },
+ }
+ },
+ }
+
+ actual = compute_ann_statistics(dataset)
+
+ self.assertEqual(expected, actual)