Merge pull request #643 from Labelbox/ms/coco-handle-empty-annotation

handle empty annotations

Author: msokoloff1

labelbox/data/annotation_types/data/raster.py

@@ -2,13 +2,16 @@
 from io import BytesIO
 from typing import Callable, Optional, Union
 from typing_extensions import Literal
-import numpy as np
-import requests
+
 from PIL import Image
 from google.api_core import retry
 from pydantic import BaseModel
 from pydantic import root_validator
+from requests.exceptions import ConnectTimeout
+import requests
+import numpy as np
 
+from labelbox.exceptions import InternalServerError
 from .base_data import BaseData
 from ..types import TypedArray
 
@@ -113,7 +116,9 @@ def value(self) -> np.ndarray:
     def set_fetch_fn(self, fn):
         object.__setattr__(self, 'fetch_remote', lambda: fn(self))
 
-    @retry.Retry(deadline=60.)
+    @retry.Retry(deadline=15.,
+                 predicate=retry.if_exception_type(ConnectTimeout,
+                                                   InternalServerError))
     def fetch_remote(self) -> bytes:
         """
         Method for accessing url.
@@ -122,6 +127,8 @@ def fetch_remote(self) -> bytes:
         simply override this function
         """
         response = requests.get(self.url)
+        if response.status_code in [500, 502, 503, 504]:
+            raise InternalServerError(response.text)
         response.raise_for_status()
         return response.content
 

labelbox/data/annotation_types/data/text.py

@@ -1,9 +1,11 @@
 from typing import Callable, Optional
 
 import requests
+from requests.exceptions import ConnectTimeout
 from google.api_core import retry
 from pydantic import root_validator
 
+from labelbox.exceptions import InternalServerError
 from .base_data import BaseData
 
 
@@ -47,7 +49,9 @@ def value(self) -> str:
     def set_fetch_fn(self, fn):
         object.__setattr__(self, 'fetch_remote', lambda: fn(self))
 
-    @retry.Retry(deadline=15.)
+    @retry.Retry(deadline=15.,
+                 predicate=retry.if_exception_type(ConnectTimeout,
+                                                   InternalServerError))
     def fetch_remote(self) -> str:
         """
         Method for accessing url.
@@ -56,6 +60,8 @@ def fetch_remote(self) -> str:
         simply override this function
         """
         response = requests.get(self.url)
+        if response.status_code in [500, 502, 503, 504]:
+            raise labelbox.exceptions.InternalServerError(response.text)
         response.raise_for_status()
         return response.text
 

labelbox/data/serialization/coco/categories.py

@@ -1,4 +1,5 @@
 import sys
+from hashlib import md5
 
 from pydantic import BaseModel
 
@@ -11,4 +12,5 @@ class Categories(BaseModel):
 
 
 def hash_category_name(name: str) -> int:
-    return hash(name) + sys.maxsize
+    return int.from_bytes(
+        md5(name.encode('utf-8')).hexdigest().encode('utf-8'), 'little')

labelbox/data/serialization/coco/instance_dataset.py

@@ -1,7 +1,7 @@
 # https://cocodataset.org/#format-data
 
 from concurrent.futures import ProcessPoolExecutor, as_completed
-from typing import Any, Dict, List, Tuple
+from typing import Any, Dict, List, Tuple, Optional
 from pathlib import Path
 
 import numpy as np
@@ -15,14 +15,16 @@
 from .image import CocoImage, get_image, get_image_id
 
 
-def mask_to_coco_object_annotation(annotation: ObjectAnnotation, annot_idx: int,
-                                   image_id: int,
-                                   category_id: int) -> COCOObjectAnnotation:
+def mask_to_coco_object_annotation(
+        annotation: ObjectAnnotation, annot_idx: int, image_id: int,
+        category_id: int) -> Optional[COCOObjectAnnotation]:
     # This is going to fill any holes into the multipolygon
     # If you need to support holes use the panoptic data format
     shapely = annotation.value.shapely.simplify(1).buffer(0)
+
     if shapely.is_empty:
-        shapely = annotation.value.shapely.simplify(1).buffer(0.01)
+        return
+
     xmin, ymin, xmax, ymax = shapely.bounds
     # Iterate over polygon once or multiple polygon for each item
     area = shapely.area
@@ -89,6 +91,19 @@ def segmentations_to_common(class_annotations: COCOObjectAnnotation,
     return annotations
 
 
+def object_annotation_to_coco(
+        annotation: ObjectAnnotation, annot_idx: int, image_id: int,
+        category_id: int) -> Optional[COCOObjectAnnotation]:
+    if isinstance(annotation.value, Mask):
+        return mask_to_coco_object_annotation(annotation, annot_idx, image_id,
+                                              category_id)
+    elif isinstance(annotation.value, (Polygon, Rectangle)):
+        return vector_to_coco_object_annotation(annotation, annot_idx, image_id,
+                                                category_id)
+    else:
+        return None
+
+
 def process_label(
     label: Label,
     idx: int,
@@ -103,20 +118,16 @@ def process_label(
     categories = {}
     for class_name in annotation_lookup:
         for annotation in annotation_lookup[class_name]:
-            if annotation.name not in categories:
-                categories[annotation.name] = hash_category_name(
-                    annotation.name)
-            if isinstance(annotation.value, Mask):
-                coco_annotations.append(
-                    mask_to_coco_object_annotation(annotation, annot_idx,
-                                                   image_id,
-                                                   categories[annotation.name]))
-            elif isinstance(annotation.value, (Polygon, Rectangle)):
-                coco_annotations.append(
-                    vector_to_coco_object_annotation(
-                        annotation, annot_idx, image_id,
-                        categories[annotation.name]))
-            annot_idx += 1
+            category_id = categories.get(annotation.name) or hash_category_name(
+                annotation.name)
+            coco_annotation = object_annotation_to_coco(annotation, annot_idx,
+                                                        image_id, category_id)
+            if coco_annotation is not None:
+                coco_annotations.append(coco_annotation)
+                if annotation.name not in categories:
+                    categories[annotation.name] = category_id
+                annot_idx += 1
+
     return image, coco_annotations, categories
 
 
@@ -147,6 +158,7 @@ def from_common(cls,
                     future.result() for future in tqdm(as_completed(futures))
                 ]
         else:
+
             results = [
                 process_label(label, idx, image_root)
                 for idx, label in enumerate(labels)