labelr 0.2.0__py3-none-any.whl → 0.3.0__py3-none-any.whl

labelr/annotate.py

@@ -1,29 +1,30 @@
 import random
 import string
 
+from openfoodfacts.types import JSONType
 from openfoodfacts.utils import get_logger
 
-try:
-    from openfoodfacts.ml.object_detection import ObjectDetectionRawResult
-    from ultralytics.engine.results import Results
-except ImportError:
-    pass
-
-
 logger = get_logger(__name__)
 
 
-def format_annotation_results_from_triton(
-    objects: list["ObjectDetectionRawResult"], image_width: int, image_height: int
-):
-    """Format annotation results from a Triton object detection model into
+def format_annotation_results_from_robotoff(
+    objects: list[JSONType],
+    image_width: int,
+    image_height: int,
+    label_mapping: dict[str, str] | None = None,
+) -> list[JSONType]:
+    """Format annotation results from Robotoff prediction endpoint into
     Label Studio format."""
     annotation_results = []
     for object_ in objects:
-        bbox = object_.bounding_box
-        category_name = object_.label
+        bounding_box = object_["bounding_box"]
+        label_name = object_["label"]
+
+        if label_mapping:
+            label_name = label_mapping.get(label_name, label_name)
+
         # These are relative coordinates (between 0.0 and 1.0)
-        y_min, x_min, y_max, x_max = bbox
+        y_min, x_min, y_max, x_max = bounding_box
         # Make sure the coordinates are within the image boundaries,
         # and convert them to percentages
         y_min = min(max(0, y_min), 1.0) * 100
@@ -51,7 +52,7 @@ def format_annotation_results_from_triton(
                     "y": y,
                     "width": width,
                     "height": height,
-                    "rectanglelabels": [category_name],
+                    "rectanglelabels": [label_name],
                 },
             },
         )

labelr/apps/datasets.py

@@ -132,7 +132,9 @@ def export(
     api_key: Annotated[Optional[str], typer.Option(envvar="LABEL_STUDIO_API_KEY")],
     repo_id: Annotated[
         Optional[str],
-        typer.Option(help="Hugging Face Datasets repository ID to convert"),
+        typer.Option(
+            help="Hugging Face Datasets repository ID to convert (only if --from or --to is `hf`)"
+        ),
     ] = None,
     label_names: Annotated[
         Optional[str],

labelr/apps/projects.py

@@ -9,7 +9,7 @@ from openfoodfacts.utils import get_logger
 from PIL import Image
 
 from ..annotate import (
-    format_annotation_results_from_triton,
+    format_annotation_results_from_robotoff,
     format_annotation_results_from_ultralytics,
 )
 from ..config import LABEL_STUDIO_DEFAULT_URL
@@ -90,16 +90,48 @@ def add_split(
     train_split: Annotated[
         float, typer.Option(help="fraction of samples to add in train split")
     ],
+    split_name: Annotated[
+        Optional[str],
+        typer.Option(
+            help="name of the split associated "
+            "with the task ID file. If --task-id-file is not provided, "
+            "this field is ignored."
+        ),
+    ],
     api_key: Annotated[str, typer.Option(envvar="LABEL_STUDIO_API_KEY")],
     project_id: Annotated[int, typer.Option(help="Label Studio project ID")],
+    train_split_name: Annotated[
+        str,
+        typer.Option(help="name of the train split"),
+    ] = "train",
+    val_split_name: Annotated[
+        str,
+        typer.Option(help="name of the validation split"),
+    ] = "val",
+    task_id_file: Annotated[
+        Optional[Path],
+        typer.Option(help="path of a text file containing IDs of samples"),
+    ] = None,
+    overwrite: Annotated[
+        bool, typer.Option(help="overwrite existing split field")
+    ] = False,
     label_studio_url: str = LABEL_STUDIO_DEFAULT_URL,
 ):
     """Update the split field of tasks in a Label Studio project.
 
+    The behavior of this command depends on the `--task-id-file` option.
+
+    If `--task-id-file` is provided, it should contain a list of task IDs,
+    one per line. The split field of these tasks will be updated to the value
+    of `--split-name`.
+
+    If `--task-id-file` is not provided, the split field of all tasks in the
+    project will be updated based on the `train_split` probability.
     The split field is set to "train" with probability `train_split`, and "val"
-    otherwise. Tasks without a split field are assigned a split based on the
-    probability, and updated in the server. Tasks with a non-null split field
-    are not updated.
+    otherwise.
+
+    In both cases, tasks with a non-null split field are not updated unless
+    the `--overwrite` flag is provided.
     """
     import random
 
@@ -108,11 +140,29 @@ def add_split(
 
     ls = LabelStudio(base_url=label_studio_url, api_key=api_key)
 
+    task_ids = None
+    if task_id_file is not None:
+        if split_name is None or split_name not in (train_split_name, val_split_name):
+            raise typer.BadParameter(
+                "--split-name is required when using --task-id-file"
+            )
+        task_ids = task_id_file.read_text().strip().split("\n")
+
     for task in ls.tasks.list(project=project_id, fields="all"):
         task: Task
+        task_id = task.id
+
         split = task.data.get("split")
-        if split is None:
-            split = "train" if random.random() < train_split else "val"
+        if split is None or overwrite:
+            if task_ids and str(task_id) in task_ids:
+                split = split_name
+            else:
+                split = (
+                    train_split_name
+                    if random.random() < train_split
+                    else val_split_name
+                )
+
             logger.info("Updating task: %s, split: %s", task.id, split)
             ls.tasks.update(task.id, data={**task.data, "split": split})
 
@@ -153,30 +203,37 @@ def annotate_from_prediction(
 
 
 class PredictorBackend(enum.Enum):
-    triton = "triton"
     ultralytics = "ultralytics"
+    robotoff = "robotoff"
 
 
 @app.command()
 def add_prediction(
     api_key: Annotated[str, typer.Option(envvar="LABEL_STUDIO_API_KEY")],
     project_id: Annotated[int, typer.Option(help="Label Studio Project ID")],
+    view_id: Annotated[
+        Optional[int],
+        typer.Option(
+            help="Label Studio View ID to filter tasks. If not provided, all tasks in the "
+            "project are processed."
+        ),
+    ] = None,
     model_name: Annotated[
         str,
         typer.Option(
-            help="Name of the object detection model to run (for Triton server) or "
+            help="Name of the object detection model to run (for Robotoff server) or "
             "of the Ultralytics zero-shot model to run."
         ),
     ] = "yolov8x-worldv2.pt",
-    triton_uri: Annotated[
+    server_url: Annotated[
         Optional[str],
-        typer.Option(help="URI (host+port) of the Triton Inference Server"),
-    ] = None,
+        typer.Option(help="The Robotoff URL if the backend is robotoff"),
+    ] = "https://robotoff.openfoodfacts.org",
     backend: Annotated[
         PredictorBackend,
         typer.Option(
-            help="Prediction backend: either use a Triton server to perform "
-            "the prediction or uses Ultralytics."
+            help="Prediction backend: either use Ultralytics to perform "
+            "the prediction or Robotoff server."
         ),
     ] = PredictorBackend.ultralytics,
     labels: Annotated[
@@ -196,8 +253,8 @@ def add_prediction(
     threshold: Annotated[
         Optional[float],
         typer.Option(
-            help="Confidence threshold for selecting bounding boxes. The default is 0.5 "
-            "for Triton backend and 0.1 for Ultralytics backend."
+            help="Confidence threshold for selecting bounding boxes. The default is 0.3 "
+            "for robotoff backend and 0.1 for ultralytics backend."
         ),
     ] = None,
     max_det: Annotated[int, typer.Option(help="Maximum numbers of detections")] = 300,
@@ -221,9 +278,7 @@ def add_prediction(
 
     import tqdm
     from label_studio_sdk.client import LabelStudio
-    from openfoodfacts.utils import get_image_from_url
-
-    from labelr.triton.object_detection import ObjectDetectionModelRegistry
+    from openfoodfacts.utils import get_image_from_url, http_session
 
     label_mapping_dict = None
     if label_mapping:
@@ -242,8 +297,6 @@ def add_prediction(
     )
     ls = LabelStudio(base_url=label_studio_url, api_key=api_key)
 
-    model: ObjectDetectionModelRegistry | "YOLO"
-
     if backend == PredictorBackend.ultralytics:
         from ultralytics import YOLO
 
@@ -258,18 +311,19 @@ def add_prediction(
             model.set_classes(labels)
         else:
             logger.warning("The model does not support setting classes directly.")
-    elif backend == PredictorBackend.triton:
-        if triton_uri is None:
-            raise typer.BadParameter("Triton URI is required for Triton backend")
+    elif backend == PredictorBackend.robotoff:
+        if server_url is None:
+            raise typer.BadParameter("--server-url is required for Robotoff backend")
 
         if threshold is None:
-            threshold = 0.5
-
-        model = ObjectDetectionModelRegistry.load(model_name)
+            threshold = 0.1
+            server_url = server_url.rstrip("/")
     else:
         raise typer.BadParameter(f"Unsupported backend: {backend}")
 
-    for task in tqdm.tqdm(ls.tasks.list(project=project_id), desc="tasks"):
+    for task in tqdm.tqdm(
+        ls.tasks.list(project=project_id, view=view_id), desc="tasks"
+    ):
         if task.total_predictions == 0:
             image_url = task.data["image_url"]
             image = typing.cast(
@@ -286,12 +340,22 @@ def add_prediction(
                 label_studio_result = format_annotation_results_from_ultralytics(
                     results, labels, label_mapping_dict
                 )
-            else:
-                output = model.detect_from_image(image, triton_uri=triton_uri)
-                results = output.select(threshold=threshold)
-                logger.info("Adding prediction to task: %s", task.id)
-                label_studio_result = format_annotation_results_from_triton(
-                    results, image.width, image.height
+            elif backend == PredictorBackend.robotoff:
+                r = http_session.get(
+                    f"{server_url}/api/v1/images/predict",
+                    params={
+                        "models": model_name,
+                        "output_image": 0,
+                        "image_url": image_url,
+                    },
+                )
+                r.raise_for_status()
+                response = r.json()
+                label_studio_result = format_annotation_results_from_robotoff(
+                    response["predictions"][model_name],
+                    image.width,
+                    image.height,
+                    label_mapping_dict,
                 )
             if dry_run:
                 logger.info("image_url: %s", image_url)
@@ -339,7 +403,7 @@ def create_dataset_file(
                 extra_meta["barcode"] = barcode
                 off_image_id = Path(extract_source_from_url(url)).stem
                 extra_meta["off_image_id"] = off_image_id
-                image_id = f"{barcode}-{off_image_id}"
+                image_id = f"{barcode}_{off_image_id}"
 
             image = get_image_from_url(url, error_raise=False)
 
@@ -351,3 +415,20 @@ def create_dataset_file(
                 image_id, url, image.width, image.height, extra_meta
             )
             f.write(json.dumps(label_studio_sample) + "\n")
+
+
+@app.command()
+def create_config_file(
+    output_file: Annotated[
+        Path, typer.Option(help="Path to the output label config file", exists=False)
+    ],
+    labels: Annotated[
+        list[str], typer.Option(help="List of class labels to use for the model")
+    ],
+):
+    """Create a Label Studio label config file for object detection tasks."""
+    from labelr.project_config import create_object_detection_label_config
+
+    config = create_object_detection_label_config(labels)
+    output_file.write_text(config)
+    logger.info("Label config file created: %s", output_file)

labelr/export.py

@@ -164,16 +164,14 @@ def export_from_ls_to_ultralytics(
 
         if has_valid_annotation:
             download_output = download_image(
-                image_url, return_bytes=True, error_raise=error_raise
+                image_url, return_struct=True, error_raise=error_raise
             )
             if download_output is None:
                 logger.error("Failed to download image: %s", image_url)
                 continue
 
-            _, image_bytes = typing.cast(tuple[Image.Image, bytes], download_output)
-
             with (images_dir / split / f"{image_id}.jpg").open("wb") as f:
-                f.write(image_bytes)
+                f.write(download_output.image_bytes)
 
     with (output_dir / "data.yaml").open("w") as f:
         f.write("path: data\n")
@@ -215,14 +213,14 @@ def export_from_hf_to_ultralytics(
 
             if download_images:
                 download_output = download_image(
-                    image_url, return_bytes=True, error_raise=error_raise
+                    image_url, return_struct=True, error_raise=error_raise
                 )
                 if download_output is None:
                     logger.error("Failed to download image: %s", image_url)
                     continue
-                _, image_bytes = download_output
+
                 with (split_images_dir / f"{image_id}.jpg").open("wb") as f:
-                    f.write(image_bytes)
+                    f.write(download_output.image_bytes)
             else:
                 image = sample["image"]
                 image.save(split_images_dir / f"{image_id}.jpg")

labelr/project_config.py

@@ -0,0 +1,45 @@
+COLORS = [
+    "blue",
+    "green",
+    "yellow",
+    "red",
+    "purple",
+    "orange",
+    "pink",
+    "brown",
+    "gray",
+    "black",
+    "white",
+]
+
+
+def create_object_detection_label_config(labels_names: list[str]) -> str:
+    """Create a Label Studio label configuration for object detection tasks.
+
+    The format is the following:
+    ```xml
+    <View>
+    <Image name="image" value="$image_url"/>
+    <RectangleLabels name="label" toName="image">
+    <Label value="nutrition-table" background="green"/>
+        <Label value="nutrition-table-small" background="blue"/>
+        <Label value="nutrition-table-small-energy" background="yellow"/>
+        <Label value="nutrition-table-text" background="red"/>
+    </RectangleLabels>
+    </View>
+    ```
+    """
+    if len(labels_names) > len(COLORS):
+        raise ValueError(
+            f"Too many labels ({len(labels_names)}) for the available colors ({len(COLORS)})."
+        )
+    labels_xml = "\n".join(
+        f'    <Label value="{label}" background="{color}"/>'
+        for label, color in zip(labels_names, COLORS[: len(labels_names)])
+    )
+    return f"""<View>
+<Image name="image" value="$image_url"/>
+<RectangleLabels name="label" toName="image">
+{labels_xml}
+</RectangleLabels>
+</View>"""

labelr/sample.py

@@ -3,7 +3,9 @@ import random
 import string
 
 import datasets
-from openfoodfacts.images import download_image
+from openfoodfacts import Flavor
+from openfoodfacts.barcode import normalize_barcode
+from openfoodfacts.images import download_image, generate_image_url
 
 logger = logging.getLogger(__name__)
 
@@ -62,17 +64,49 @@ def format_object_detection_sample_from_hf(hf_sample: dict, split: str) -> dict:
     annotation_results = format_annotation_results_from_hf(
         objects, image_width, image_height
     )
+    image_id = hf_sample["image_id"]
+    image_url = hf_meta["image_url"]
+    meta_kwargs = {}
+
+    if "off_image_id" in hf_meta:
+        # If `off_image_id` is present, we assume this is an Open Food Facts
+        # dataset sample.
+        # We normalize the barcode, and generate a new image URL
+        # to make sure that:
+        # - the image URL is valid with correct path
+        # - we use the images subdomain everywhere
+        off_image_id = hf_meta["off_image_id"]
+        meta_kwargs["off_image_id"] = off_image_id
+        barcode = normalize_barcode(hf_meta["barcode"])
+        meta_kwargs["barcode"] = barcode
+        image_id = f"{barcode}_{off_image_id}"
+
+        if ".openfoodfacts." in image_url:
+            flavor = Flavor.off
+        elif ".openbeautyfacts." in image_url:
+            flavor = Flavor.obf
+        elif ".openpetfoodfacts." in image_url:
+            flavor = Flavor.opf
+        elif ".openproductsfacts." in image_url:
+            flavor = Flavor.opf
+        else:
+            raise ValueError(
+                f"Unknown Open Food Facts flavor for image URL: {image_url}"
+            )
+        image_url = generate_image_url(
+            code=barcode, image_id=off_image_id, flavor=flavor
+        )
+
     return {
         "data": {
-            "image_id": hf_sample["image_id"],
-            "image_url": hf_meta["image_url"],
+            "image_id": image_id,
+            "image_url": image_url,
             "batch": "null",
             "split": split,
             "meta": {
                 "width": image_width,
                 "height": image_height,
-                "barcode": hf_meta["barcode"],
-                "off_image_id": hf_meta["off_image_id"],
+                **meta_kwargs,
             },
         },
         "predictions": [{"result": annotation_results}],

{labelr-0.2.0.dist-info → labelr-0.3.0.dist-info}/METADATA

@@ -1,7 +1,7 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: labelr
-Version: 0.2.0
-Summary: Add your description here
+Version: 0.3.0
+Summary: A command-line tool to manage labeling tasks with Label Studio.
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -9,14 +9,11 @@ Requires-Dist: datasets>=3.2.0
 Requires-Dist: imagehash>=4.3.1
 Requires-Dist: label-studio-sdk>=1.0.8
 Requires-Dist: more-itertools>=10.5.0
-Requires-Dist: openfoodfacts>=2.3.4
-Requires-Dist: protobuf>=5.29.1
+Requires-Dist: openfoodfacts>=2.9.0
 Requires-Dist: typer>=0.15.1
 Provides-Extra: ultralytics
 Requires-Dist: ultralytics>=8.3.49; extra == "ultralytics"
-Provides-Extra: triton
-Requires-Dist: tritonclient>=2.52.0; extra == "triton"
-Requires-Dist: openfoodfacts[ml]>=2.3.4; extra == "triton"
+Dynamic: license-file
 
 # Labelr
 
@@ -67,7 +64,17 @@ For all the commands that interact with Label Studio, you need to provide an API
 
 #### Create a project
 
-Once you have a Label Studio instance running, you can create a project with the following command:
+Once you have a Label Studio instance running, you can create a project easily. First, you need to create a configuration file for the project. The configuration file is an XML file that defines the labeling interface and the labels to use for the project. You can find an example of a configuration file in the [Label Studio documentation](https://labelstud.io/guide/setup).
+
+For an object detection task, a command allows you to create the configuration file automatically:
+
+```bash
+labelr projects create-config --labels 'label1' --labels 'label2' --output-file label_config.xml
+```
+
+where `label1` and `label2` are the labels you want to use for the object detection task, and `label_config.xml` is the output file that will contain the configuration.
+
+Then, you can create a project on Label Studio with the following command:
 
 ```bash
 labelr projects create --title my_project --api-key API_KEY --config-file label_config.xml

labelr-0.3.0.dist-info/RECORD

@@ -0,0 +1,20 @@
+labelr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+labelr/__main__.py,sha256=G4e95-IfhI-lOmkOBP6kQ8wl1x_Fl7dZlLOYr90K83c,66
+labelr/annotate.py,sha256=3fJ9FYbcozcOoKuhNtzPHV8sSnp-45FsNnMc8UeBHGU,3503
+labelr/check.py,sha256=3wK6mE0UsKvoBNm0_lyWhCMq7gxkv5r50pvO70damXY,2476
+labelr/config.py,sha256=3RXF_NdkSuHvfVMGMlYmjlw45fU77zQkLX7gmZq7NxM,64
+labelr/export.py,sha256=MuU7M0H1THg3FcA6IEYPKFb58nIakNCCpcItQSSwNzM,10070
+labelr/main.py,sha256=gQ8I287mpLy3HIUWqZUyoLAfPwkphwOIzut7hEbH8tY,2135
+labelr/project_config.py,sha256=CIHEcgSOfXb53naHWEBkTDm2V9m3abAu8C54VSzHjAs,1260
+labelr/sample.py,sha256=WPWKJbyFDp1T-pmd1DfCpz2LWUApGJ71MvnMYkHeORU,7164
+labelr/types.py,sha256=CahqnkLnGj23Jg0X9nftK7Jiorq50WYQqR8u9Ln4E-k,281
+labelr/apps/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+labelr/apps/datasets.py,sha256=OihvNIaqvny9QH64kq3oUrITRppGPz6WlJUSeObS3kE,7991
+labelr/apps/projects.py,sha256=mF25efdNsNaOyMJindi60EHdKP6kR_7L6KFBEbqMlqM,15146
+labelr/apps/users.py,sha256=twQSlpHxE0hrYkgrJpEFbK8lYfWnpJr8vyfLHLtdAUU,909
+labelr-0.3.0.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+labelr-0.3.0.dist-info/METADATA,sha256=bxgaoKo6fCFfTtFI2YSjb_cSDbURB_JDsMA_5PV09gs,6583
+labelr-0.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+labelr-0.3.0.dist-info/entry_points.txt,sha256=OACukVeR_2z54i8yQuWqqk_jdEHlyTwmTFOFBmxPp1k,43
+labelr-0.3.0.dist-info/top_level.txt,sha256=bjZo50aGZhXIcZYpYOX4sdAQcamxh8nwfEh7A9RD_Ag,7
+labelr-0.3.0.dist-info/RECORD,,

{labelr-0.2.0.dist-info → labelr-0.3.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.6.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

labelr-0.2.0.dist-info/RECORD

@@ -1,19 +0,0 @@
-labelr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-labelr/__main__.py,sha256=G4e95-IfhI-lOmkOBP6kQ8wl1x_Fl7dZlLOYr90K83c,66
-labelr/annotate.py,sha256=aphaxyGvKVTjB4DQvj00HpX-X8Xz70UHoKSf4QFWaO4,3456
-labelr/check.py,sha256=3wK6mE0UsKvoBNm0_lyWhCMq7gxkv5r50pvO70damXY,2476
-labelr/config.py,sha256=3RXF_NdkSuHvfVMGMlYmjlw45fU77zQkLX7gmZq7NxM,64
-labelr/export.py,sha256=tcOmVnOdJidWfNouNWoQ4OJgHMbbG-bLFHkId9huiS0,10170
-labelr/main.py,sha256=gQ8I287mpLy3HIUWqZUyoLAfPwkphwOIzut7hEbH8tY,2135
-labelr/sample.py,sha256=cpzvgZWVU6GzwD35tqGKEFVKAgqQbSHlWW6IL9FG15Q,5918
-labelr/types.py,sha256=CahqnkLnGj23Jg0X9nftK7Jiorq50WYQqR8u9Ln4E-k,281
-labelr/apps/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-labelr/apps/datasets.py,sha256=DXU8XZx0iEHDI5SvUeI8atCKSUmj9YJwO6xTgMZDgEI,7936
-labelr/apps/projects.py,sha256=HpulSciBVTk1sSR1uXjtHytny9t-rN8wiaQ5llNBX6Y,12420
-labelr/apps/users.py,sha256=twQSlpHxE0hrYkgrJpEFbK8lYfWnpJr8vyfLHLtdAUU,909
-labelr-0.2.0.dist-info/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-labelr-0.2.0.dist-info/METADATA,sha256=nxbEiMBsVEQS71pzZ39uLL_GCVebIB71wyxvFsueGcU,5960
-labelr-0.2.0.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-labelr-0.2.0.dist-info/entry_points.txt,sha256=OACukVeR_2z54i8yQuWqqk_jdEHlyTwmTFOFBmxPp1k,43
-labelr-0.2.0.dist-info/top_level.txt,sha256=bjZo50aGZhXIcZYpYOX4sdAQcamxh8nwfEh7A9RD_Ag,7
-labelr-0.2.0.dist-info/RECORD,,