Fix image stats when no image info available (#29)

* Fix image stats when no image info available

* Update changelog

CHANGELOG.md

@@ -76,6 +76,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   (<https://github.com/cvat-ai/datumaro/pull/9>, <https://github.com/cvat-ai/datumaro/pull/16>)
 - Missing comparison of the base class attributes in the `Mask` class
   (<https://github.com/cvat-ai/datumaro/pull/28>)
+- Image stats when no image info available for some images in the dataset
+  (<https://github.com/cvat-ai/datumaro/pull/29>)
 
 ### Security
 - TBD

datumaro/components/operations.py

@@ -1320,8 +1320,15 @@ def __init__(self):
         self._stats = {}  # (id, subset) -> (pixel count, mean vec, std vec)
 
     def accumulate(self, item: DatasetItem):
+        if not isinstance(item.media, Image):
+            log.warning(
+                "Item %s: has no image info, the image will be skipped from pixel statistics",
+                item.id,
+            )
+            return
+
         size = item.media.size
-        if size is None:
+        if size is None or not item.media.has_data:
             log.warning(
                 "Item %s: can't detect image size, "
                 "the image will be skipped from pixel statistics",

tests/test_ops.py

@@ -95,6 +95,30 @@ def test_image_stats(self):
         for estd, astd in zip(expected_std, actual_std):
             self.assertAlmostEqual(estd, astd, places=0)
 
+    @mark_requirement(Requirements.DATUM_GENERAL_REQ)
+    def test_image_stats_with_no_image_infos(self):
+        dataset = Dataset.from_iterable(
+            [
+                DatasetItem(id=0, media=Image(size=(10, 10))),
+                DatasetItem(id=1, media=Image(path="inexistent.path")),
+                DatasetItem(id=2),
+            ]
+        )
+
+        actual = compute_image_statistics(dataset)
+
+        self.assertEqual(
+            actual["dataset"],
+            {
+                "images count": 3,
+                "unique images count": 3,
+                "repeated images count": 0,
+                "repeated images": [],
+            },
+        )
+        self.assertEqual("n/a", actual["subsets"]["default"]["image mean"])
+        self.assertEqual("n/a", actual["subsets"]["default"]["image std"])
+
     @mark_requirement(Requirements.DATUM_GENERAL_REQ)
     def test_stats(self):
         dataset = Dataset.from_iterable(