scale-nucleus 0.17.5__tar.gz → 0.17.6b0__tar.gz

{scale_nucleus-0.17.5 → scale_nucleus-0.17.6b0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: scale-nucleus
-Version: 0.17.5
+Version: 0.17.6b0
 Summary: The official Python client library for Nucleus, the Data Platform for AI
 Home-page: https://scale.com/nucleus
 License: MIT
@@ -14,6 +14,7 @@ Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
 Provides-Extra: launch
 Provides-Extra: metrics
 Requires-Dist: Pillow (>=7.1.2)

{scale_nucleus-0.17.5 → scale_nucleus-0.17.6b0}/nucleus/dataset.py

@@ -997,9 +997,9 @@ class Dataset:
             raise Exception("Must provide at least one list of internal IDs")
         payload = {
             NAME_KEY: name,
-            DATASET_ITEM_IDS_KEY: dataset_item_ids
-            if dataset_item_ids
-            else None,
+            DATASET_ITEM_IDS_KEY: (
+                dataset_item_ids if dataset_item_ids else None
+            ),
             SCENE_IDS_KEY: scene_ids if scene_ids else None,
             OBJECT_IDS_KEY: [*(annotation_ids or []), *(prediction_ids or [])]
             or None,
@@ -1449,6 +1449,67 @@ class Dataset:
         )
         return convert_export_payload(api_payload[EXPORTED_ROWS])
 
+    def scene_and_annotation_generator(self, page_size: int = 10):
+        """Provides a generator of all Scenes and Annotations in the dataset grouped by scene.
+
+        Args:
+            page_size: Number of scenes to fetch per page. Default is 10.
+
+        Returns:
+            Generator where each element is a nested dict containing scene and annotation information of the dataset structured as a JSON.
+
+            Track grouping is slightly more complicated and is done in the following order:
+            1. If track_id is defined in the annotations table, use it as the track id.
+            2. If track_reference_id is defined in the metadata field of the annotations table, use it as the track id.
+            3. If track_id is defined in the metadata field of the annotations table, use it as the track id.
+            4. If track_id is not defined and annotation_id is defined, use annotation_id as track id.
+            5. If annotation_id grouping is unsuccessful such that the annotation id is unique across all frames in the scene for all annotations, throw an error that the annotation format is incompatible.
+            6. If there is no track or annotation id, throw an error that the annotation format is incompatible.
+
+            If you use the generator and discover that no scenes were generated, check the response error message for more information. It is likely that the annotations are not in the correct format.
+
+            ::
+            Iterable[{
+                "scene": {
+                    "id": str,
+                    "reference_id": str,
+                    "metadata": Dict[str, Any]
+                    "type": str,
+                    "fileLocation": str,
+                }
+                "annotations": {
+                    "{trackId}": {
+                        "label": str,
+                        "name": str,
+                        "frames": List[{
+                            "left": int,
+                            "top": int,
+                            "width": int,
+                            "height": int,
+                            "key": str, # frame key
+                            "metadata": Dict[str, Any]
+                        }]
+                    }
+                }
+            }]
+
+            This is similar to how the Scale API returns task data
+        """
+
+        if page_size > 30:
+            raise ValueError("Page size must be less than or equal to 30")
+
+        endpoint_name = "exportForTrainingByScene"
+        json_generator = paginate_generator(
+            client=self._client,
+            endpoint=f"dataset/{self.id}/{endpoint_name}",
+            result_key=EXPORT_FOR_TRAINING_KEY,
+            page_size=page_size,
+        )
+
+        for data in json_generator:
+            yield data
+
     def items_and_annotation_generator(
         self,
         query: Optional[str] = None,
@@ -2310,9 +2371,9 @@ class Dataset:
         pointcloud_ref_id: str,
         predictions_s3_path: str,
     ):
-        """Upload Lidar Semantic Segmentation predictions for a given pointcloud.
+        """Upload Lidar Semantic Segmentation predictions for a given point-cloud.
 
-        Assuming a pointcloud with only 4 points (three labeled as Car, one labeled as Person),
+        Assuming a point-cloud with only 4 points (three labeled as Car, one labeled as Person),
         the contents of the predictions s3 object should be formatted as such:
 
         .. code-block:: json

{scale_nucleus-0.17.5 → scale_nucleus-0.17.6b0}/pyproject.toml

@@ -25,7 +25,7 @@ ignore = ["E501", "E741", "E731", "F401"]  # Easy ignore for getting it running
 
 [tool.poetry]
 name = "scale-nucleus"
-version = "0.17.5"
+version = "0.17.6b0"
 description = "The official Python client library for Nucleus, the Data Platform for AI"
 license =  "MIT"
 authors = ["Scale AI Nucleus Team <nucleusapi@scaleapi.com>"]