scale-nucleus 0.1.10__py3-none-any.whl → 0.1.24__py3-none-any.whl

nucleus/annotation.py

@@ -2,40 +2,38 @@ import json
 from dataclasses import dataclass
 from enum import Enum
 from typing import Dict, List, Optional, Sequence, Union
-from nucleus.dataset_item import is_local_path
+from urllib.parse import urlparse
 
 from .constants import (
     ANNOTATION_ID_KEY,
     ANNOTATIONS_KEY,
     BOX_TYPE,
-    DATASET_ITEM_ID_KEY,
+    CATEGORY_TYPE,
+    CUBOID_TYPE,
+    DIMENSIONS_KEY,
     GEOMETRY_KEY,
     HEIGHT_KEY,
     INDEX_KEY,
-    ITEM_ID_KEY,
     LABEL_KEY,
     MASK_TYPE,
     MASK_URL_KEY,
     METADATA_KEY,
     POLYGON_TYPE,
+    POSITION_KEY,
     REFERENCE_ID_KEY,
+    TAXONOMY_NAME_KEY,
     TYPE_KEY,
     VERTICES_KEY,
     WIDTH_KEY,
     X_KEY,
+    YAW_KEY,
     Y_KEY,
+    Z_KEY,
 )
 
 
 class Annotation:
-    reference_id: Optional[str] = None
-    item_id: Optional[str] = None
-
-    def _check_ids(self):
-        if bool(self.reference_id) == bool(self.item_id):
-            raise Exception(
-                "You must specify either a reference_id or an item_id for an annotation."
-            )
+    reference_id: str
 
     @classmethod
     def from_json(cls, payload: dict):
@@ -43,6 +41,10 @@ class Annotation:
             return BoxAnnotation.from_json(payload)
         elif payload.get(TYPE_KEY, None) == POLYGON_TYPE:
             return PolygonAnnotation.from_json(payload)
+        elif payload.get(TYPE_KEY, None) == CUBOID_TYPE:
+            return CuboidAnnotation.from_json(payload)
+        elif payload.get(TYPE_KEY, None) == CATEGORY_TYPE:
+            return CategoryAnnotation.from_json(payload)
         else:
             return SegmentationAnnotation.from_json(payload)
 
@@ -84,14 +86,12 @@ class Segment:
 class SegmentationAnnotation(Annotation):
     mask_url: str
     annotations: List[Segment]
+    reference_id: str
     annotation_id: Optional[str] = None
-    reference_id: Optional[str] = None
-    item_id: Optional[str] = None
 
     def __post_init__(self):
         if not self.mask_url:
             raise Exception("You must specify a mask_url.")
-        self._check_ids()
 
     @classmethod
     def from_json(cls, payload: dict):
@@ -103,8 +103,7 @@ class SegmentationAnnotation(Annotation):
                 Segment.from_json(ann)
                 for ann in payload.get(ANNOTATIONS_KEY, [])
             ],
-            reference_id=payload.get(REFERENCE_ID_KEY, None),
-            item_id=payload.get(ITEM_ID_KEY, None),
+            reference_id=payload[REFERENCE_ID_KEY],
             annotation_id=payload.get(ANNOTATION_ID_KEY, None),
         )
 
@@ -115,16 +114,17 @@ class SegmentationAnnotation(Annotation):
             ANNOTATIONS_KEY: [ann.to_payload() for ann in self.annotations],
             ANNOTATION_ID_KEY: self.annotation_id,
         }
-        if self.reference_id:
-            payload[REFERENCE_ID_KEY] = self.reference_id
-        else:
-            payload[ITEM_ID_KEY] = self.item_id
+
+        payload[REFERENCE_ID_KEY] = self.reference_id
+
         return payload
 
 
 class AnnotationTypes(Enum):
     BOX = BOX_TYPE
     POLYGON = POLYGON_TYPE
+    CUBOID = CUBOID_TYPE
+    CATEGORY = CATEGORY_TYPE
 
 
 @dataclass  # pylint: disable=R0902
@@ -134,14 +134,14 @@ class BoxAnnotation(Annotation):  # pylint: disable=R0902
     y: Union[float, int]
     width: Union[float, int]
     height: Union[float, int]
-    reference_id: Optional[str] = None
-    item_id: Optional[str] = None
+    reference_id: str
     annotation_id: Optional[str] = None
     metadata: Optional[Dict] = None
 
     def __post_init__(self):
-        self._check_ids()
         self.metadata = self.metadata if self.metadata else {}
+        if self.annotation_id is None:
+            self.annotation_id = f"{self.label}-{self.x}-{self.y}-{self.width}-{self.height}-{self.reference_id}"
 
     @classmethod
     def from_json(cls, payload: dict):
@@ -152,8 +152,7 @@ class BoxAnnotation(Annotation):  # pylint: disable=R0902
             y=geometry.get(Y_KEY, 0),
             width=geometry.get(WIDTH_KEY, 0),
             height=geometry.get(HEIGHT_KEY, 0),
-            reference_id=payload.get(REFERENCE_ID_KEY, None),
-            item_id=payload.get(DATASET_ITEM_ID_KEY, None),
+            reference_id=payload[REFERENCE_ID_KEY],
             annotation_id=payload.get(ANNOTATION_ID_KEY, None),
             metadata=payload.get(METADATA_KEY, {}),
         )
@@ -187,17 +186,29 @@ class Point:
         return {X_KEY: self.x, Y_KEY: self.y}
 
 
+@dataclass
+class Point3D:
+    x: float
+    y: float
+    z: float
+
+    @classmethod
+    def from_json(cls, payload: Dict[str, float]):
+        return cls(payload[X_KEY], payload[Y_KEY], payload[Z_KEY])
+
+    def to_payload(self) -> dict:
+        return {X_KEY: self.x, Y_KEY: self.y, Z_KEY: self.z}
+
+
 @dataclass
 class PolygonAnnotation(Annotation):
     label: str
     vertices: List[Point]
-    reference_id: Optional[str] = None
-    item_id: Optional[str] = None
+    reference_id: str
     annotation_id: Optional[str] = None
     metadata: Optional[Dict] = None
 
     def __post_init__(self):
-        self._check_ids()
         self.metadata = self.metadata if self.metadata else {}
         if len(self.vertices) > 0:
             if not hasattr(self.vertices[0], X_KEY) or not hasattr(
@@ -221,8 +232,7 @@ class PolygonAnnotation(Annotation):
             vertices=[
                 Point.from_json(_) for _ in geometry.get(VERTICES_KEY, [])
             ],
-            reference_id=payload.get(REFERENCE_ID_KEY, None),
-            item_id=payload.get(DATASET_ITEM_ID_KEY, None),
+            reference_id=payload[REFERENCE_ID_KEY],
             annotation_id=payload.get(ANNOTATION_ID_KEY, None),
             metadata=payload.get(METADATA_KEY, {}),
         )
@@ -241,12 +251,91 @@ class PolygonAnnotation(Annotation):
         return payload
 
 
-def check_all_annotation_paths_remote(
+@dataclass  # pylint: disable=R0902
+class CuboidAnnotation(Annotation):  # pylint: disable=R0902
+    label: str
+    position: Point3D
+    dimensions: Point3D
+    yaw: float
+    reference_id: str
+    annotation_id: Optional[str] = None
+    metadata: Optional[Dict] = None
+
+    def __post_init__(self):
+        self.metadata = self.metadata if self.metadata else {}
+
+    @classmethod
+    def from_json(cls, payload: dict):
+        geometry = payload.get(GEOMETRY_KEY, {})
+        return cls(
+            label=payload.get(LABEL_KEY, 0),
+            position=Point3D.from_json(geometry.get(POSITION_KEY, {})),
+            dimensions=Point3D.from_json(geometry.get(DIMENSIONS_KEY, {})),
+            yaw=geometry.get(YAW_KEY, 0),
+            reference_id=payload[REFERENCE_ID_KEY],
+            annotation_id=payload.get(ANNOTATION_ID_KEY, None),
+            metadata=payload.get(METADATA_KEY, {}),
+        )
+
+    def to_payload(self) -> dict:
+        payload = {
+            LABEL_KEY: self.label,
+            TYPE_KEY: CUBOID_TYPE,
+            GEOMETRY_KEY: {
+                POSITION_KEY: self.position.to_payload(),
+                DIMENSIONS_KEY: self.dimensions.to_payload(),
+                YAW_KEY: self.yaw,
+            },
+        }
+        payload[REFERENCE_ID_KEY] = self.reference_id
+        if self.annotation_id:
+            payload[ANNOTATION_ID_KEY] = self.annotation_id
+        if self.metadata:
+            payload[METADATA_KEY] = self.metadata
+
+        return payload
+
+
+@dataclass
+class CategoryAnnotation(Annotation):
+    label: str
+    taxonomy_name: str
+    reference_id: str
+    metadata: Optional[Dict] = None
+
+    def __post_init__(self):
+        self.metadata = self.metadata if self.metadata else {}
+
+    @classmethod
+    def from_json(cls, payload: dict):
+        return cls(
+            label=payload[LABEL_KEY],
+            taxonomy_name=payload[TAXONOMY_NAME_KEY],
+            reference_id=payload[REFERENCE_ID_KEY],
+            metadata=payload.get(METADATA_KEY, {}),
+        )
+
+    def to_payload(self) -> dict:
+        return {
+            LABEL_KEY: self.label,
+            TAXONOMY_NAME_KEY: self.taxonomy_name,
+            TYPE_KEY: CATEGORY_TYPE,
+            GEOMETRY_KEY: {},
+            REFERENCE_ID_KEY: self.reference_id,
+            METADATA_KEY: self.metadata,
+        }
+
+
+def is_local_path(path: str) -> bool:
+    return urlparse(path).scheme not in {"https", "http", "s3", "gs"}
+
+
+def check_all_mask_paths_remote(
     annotations: Sequence[Union[Annotation]],
 ):
     for annotation in annotations:
         if hasattr(annotation, MASK_URL_KEY):
             if is_local_path(getattr(annotation, MASK_URL_KEY)):
                 raise ValueError(
-                    f"Found an annotation with a local path, which cannot be uploaded asynchronously. Use a remote path instead. {annotation}"
+                    f"Found an annotation with a local path, which is not currently supported. Use a remote path instead. {annotation}"
                 )

nucleus/autocurate.py

@@ -0,0 +1,26 @@
+import datetime
+import requests
+from nucleus.constants import (
+    JOB_CREATION_TIME_KEY,
+    JOB_LAST_KNOWN_STATUS_KEY,
+    JOB_TYPE_KEY,
+)
+from nucleus.job import AsyncJob
+
+
+def entropy(name, model_run, client):
+    model_run_ids = [model_run.model_run_id]
+    dataset_id = model_run.dataset_id
+    response = client.make_request(
+        payload={"modelRunIds": model_run_ids},
+        route=f"autocurate/{dataset_id}/single_model_entropy/{name}",
+        requests_command=requests.post,
+    )
+    # TODO: the response should already have the below three fields populated
+    response[JOB_LAST_KNOWN_STATUS_KEY] = "Started"
+    response[JOB_TYPE_KEY] = "autocurateEntropy"
+    response[JOB_CREATION_TIME_KEY] = (
+        datetime.datetime.now().isoformat("T", "milliseconds") + "Z"
+    )
+    job = AsyncJob.from_json(response, client)
+    return job

nucleus/constants.py

@@ -7,38 +7,64 @@ BOX_TYPE = "box"
 POLYGON_TYPE = "polygon"
 MASK_TYPE = "mask"
 SEGMENTATION_TYPE = "segmentation"
-ANNOTATION_TYPES = (BOX_TYPE, POLYGON_TYPE, SEGMENTATION_TYPE)
+CUBOID_TYPE = "cuboid"
+CATEGORY_TYPE = "category"
+MULTICATEGORY_TYPE = "multicategory"
+ANNOTATION_TYPES = (
+    BOX_TYPE,
+    POLYGON_TYPE,
+    SEGMENTATION_TYPE,
+    CUBOID_TYPE,
+    CATEGORY_TYPE,
+)
 ANNOTATION_UPDATE_KEY = "update"
 AUTOTAGS_KEY = "autotags"
+AUTOTAG_SCORE_THRESHOLD = "score_threshold"
 EXPORTED_ROWS = "exportedRows"
+CAMERA_PARAMS_KEY = "camera_params"
 CLASS_PDF_KEY = "class_pdf"
 CONFIDENCE_KEY = "confidence"
+CX_KEY = "cx"
+CY_KEY = "cy"
 DATASET_ID_KEY = "dataset_id"
-DATASET_ITEM_IDS_KEY = "dataset_item_ids"
-DATASET_ITEM_ID_KEY = "dataset_item_id"
 DATASET_LENGTH_KEY = "length"
 DATASET_MODEL_RUNS_KEY = "model_run_ids"
 DATASET_NAME_KEY = "name"
 DATASET_SLICES_KEY = "slice_ids"
 DEFAULT_ANNOTATION_UPDATE_MODE = False
 DEFAULT_NETWORK_TIMEOUT_SEC = 120
-EMBEDDINGS_URL_KEY = "embeddings_url"
+DIMENSIONS_KEY = "dimensions"
+EMBEDDINGS_URL_KEY = "embeddings_urls"
+EMBEDDING_DIMENSION_KEY = "embedding_dimension"
 ERRORS_KEY = "errors"
 ERROR_CODES = "error_codes"
 ERROR_ITEMS = "upload_errors"
 ERROR_PAYLOAD = "error_payload"
+FRAMES_KEY = "frames"
+FX_KEY = "fx"
+FY_KEY = "fy"
 GEOMETRY_KEY = "geometry"
+HEADING_KEY = "heading"
 HEIGHT_KEY = "height"
 IGNORED_ITEMS = "ignored_items"
 IMAGE_KEY = "image"
+IMAGE_LOCATION_KEY = "image_location"
 IMAGE_URL_KEY = "image_url"
 INDEX_KEY = "index"
+INDEX_CONTINUOUS_ENABLE_KEY = "enable"
 ITEMS_KEY = "items"
-ITEM_ID_KEY = "item_id"
 ITEM_KEY = "item"
+ITEMS_KEY = "items"
 ITEM_METADATA_SCHEMA_KEY = "item_metadata_schema"
 JOB_ID_KEY = "job_id"
+KEEP_HISTORY_KEY = "keep_history"
+LENGTH_KEY = "length"
+JOB_STATUS_KEY = "job_status"
+JOB_LAST_KNOWN_STATUS_KEY = "job_last_known_status"
+JOB_TYPE_KEY = "job_type"
+JOB_CREATION_TIME_KEY = "job_creation_time"
 LABEL_KEY = "label"
+LABELS_KEY = "labels"
 MASK_URL_KEY = "mask_url"
 MESSAGE_KEY = "message"
 METADATA_KEY = "metadata"
@@ -47,21 +73,33 @@ MODEL_RUN_ID_KEY = "model_run_id"
 NAME_KEY = "name"
 NEW_ITEMS = "new_items"
 NUCLEUS_ENDPOINT = "https://api.scale.com/v1/nucleus"
+NUM_SENSORS_KEY = "num_sensors"
 ORIGINAL_IMAGE_URL_KEY = "original_image_url"
+POINTCLOUD_KEY = "pointcloud"
+POINTCLOUD_LOCATION_KEY = "pointcloud_location"
+POINTCLOUD_URL_KEY = "pointcloud_url"
+POSITION_KEY = "position"
 PREDICTIONS_IGNORED_KEY = "predictions_ignored"
 PREDICTIONS_PROCESSED_KEY = "predictions_processed"
 REFERENCE_IDS_KEY = "reference_ids"
 REFERENCE_ID_KEY = "reference_id"
 REQUEST_ID_KEY = "requestId"
+SCENES_KEY = "scenes"
 SEGMENTATIONS_KEY = "segmentations"
 SLICE_ID_KEY = "slice_id"
 STATUS_CODE_KEY = "status_code"
 STATUS_KEY = "status"
 SUCCESS_STATUS_CODES = [200, 201, 202]
+TAXONOMY_NAME_KEY = "taxonomy_name"
 TYPE_KEY = "type"
 UPDATED_ITEMS = "updated_items"
 UPDATE_KEY = "update"
+UPLOAD_TO_SCALE_KEY = "upload_to_scale"
+URL_KEY = "url"
 VERTICES_KEY = "vertices"
 WIDTH_KEY = "width"
+YAW_KEY = "yaw"
+W_KEY = "w"
 X_KEY = "x"
 Y_KEY = "y"
+Z_KEY = "z"