feat: datumaro 1.2.0

Signed-off-by: Inhyuk Andy Cho <andy.inhyuk.jo@intel.com>
openvinotoolkit · Apr 18, 2023 · 862f086 · 862f086
1 parent bbbeb4e
commit 862f086
Show file tree

Hide file tree

Showing 5 changed files with 14 additions and 6 deletions.
diff --git a/otx/algorithms/classification/adapters/mmcls/models/classifiers/mixin.py b/otx/algorithms/classification/adapters/mmcls/models/classifiers/mixin.py
@@ -49,7 +49,11 @@ def _convert_anns(item: DatasetItemEntityWithID):
                 dm.DatasetItem(
                     id=item.id_,
                     subset="train",
-                    media=dm.Image(path=item.media.path, size=(item.media.height, item.media.width)),
+                    media=dm.Image.from_file(path=item.media.path, size=(item.media.height, item.media.width))
+                    if item.media.path
+                    else dm.Image.from_numpy(
+                        data=getattr(item.media, "_Image__data"), size=(item.media.height, item.media.width)
+                    ),
                     annotations=_convert_anns(item),
                 )
                 for item in otx_dataset

diff --git a/otx/core/data/caching/storage_cache.py b/otx/core/data/caching/storage_cache.py
@@ -10,6 +10,7 @@
 from typing import List, Optional
 
 from datumaro.components.dataset import Dataset as DatumDataset
+from datumaro.components.progress_reporting import SimpleProgressReporter
 
 from otx.core.file import OTX_CACHE
 
@@ -85,6 +86,7 @@ def get_file_hash(file):
         save_media=True,
         image_ext=scheme,
         num_workers=num_workers,
+        progress_reporter=SimpleProgressReporter(0, 10),
     )
 
     cache_paths = []

diff --git a/otx/core/data/manager/dataset_manager.py b/otx/core/data/manager/dataset_manager.py
@@ -6,7 +6,7 @@
 
 # pylint: disable=invalid-name
 import os
-from typing import List, Tuple, Union
+from typing import List, Optional, Tuple, Union
 
 import datumaro
 from datumaro.components.dataset import Dataset, DatasetSubset
@@ -73,9 +73,11 @@ def get_data_format(data_root: str) -> str:
         return data_format
 
     @staticmethod
-    def get_image_path(data_item: DatasetItem) -> str:
+    def get_image_path(data_item: DatasetItem) -> Optional[str]:
         """Returns the path of image."""
-        return data_item.media.path
+        if hasattr(data_item.media, "path"):
+            return data_item.media.path
+        return None
 
     @staticmethod
     def export_dataset(dataset: Dataset, output_dir: str, data_format: str, save_media=True):

diff --git a/requirements/base.txt b/requirements/base.txt
@@ -4,7 +4,7 @@ natsort>=6.0.0
 prettytable
 protobuf>=3.20.0
 pyyaml
-datumaro==1.0.0rc1
+datumaro==1.2.0rc3
 psutil
 scipy>=1.8
 bayesian-optimization>=1.2.0

diff --git a/tests/unit/core/data/manager/test_dataset_manager.py b/tests/unit/core/data/manager/test_dataset_manager.py
@@ -74,7 +74,7 @@ def test_get_image_path(self, task, subset):
         random_data = DatasetManager.get_image_path(
             generate_datumaro_dataset_item(item_id="0", subset=subset, task=task)
         )
-        assert random_data is not None
+        assert random_data is None
 
     @e2e_pytest_unit
     @pytest.mark.parametrize("task", AVAILABLE_TASKS)