labelr 0.6.0__tar.gz → 0.7.0__tar.gz

{labelr-0.6.0/src/labelr.egg-info → labelr-0.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: labelr
-Version: 0.6.0
+Version: 0.7.0
 Summary: A command-line tool to manage labeling tasks with Label Studio.
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
@@ -12,8 +12,11 @@ Requires-Dist: more-itertools>=10.5.0
 Requires-Dist: openfoodfacts>=2.9.0
 Requires-Dist: typer>=0.15.1
 Requires-Dist: google-cloud-batch==0.18.0
+Requires-Dist: huggingface-hub
 Provides-Extra: ultralytics
-Requires-Dist: ultralytics>=8.3.49; extra == "ultralytics"
+Requires-Dist: ultralytics==8.3.223; extra == "ultralytics"
+Provides-Extra: fiftyone
+Requires-Dist: fiftyone~=1.10.0; extra == "fiftyone"
 Dynamic: license-file
 
 # Labelr

{labelr-0.6.0 → labelr-0.7.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "labelr"
-version = "0.6.0"
+version = "0.7.0"
 description = "A command-line tool to manage labeling tasks with Label Studio."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -12,6 +12,7 @@ dependencies = [
     "openfoodfacts>=2.9.0",
     "typer>=0.15.1",
     "google-cloud-batch==0.18.0",
+    "huggingface-hub"
 ]
 
 [project.scripts]
@@ -19,7 +20,10 @@ labelr = "labelr.main:app"
 
 [project.optional-dependencies]
 ultralytics = [
-    "ultralytics>=8.3.49",
+    "ultralytics==8.3.223",
+]
+fiftyone = [
+    "fiftyone~=1.10.0"
 ]
 
 [tool.uv]

{labelr-0.6.0 → labelr-0.7.0}/src/labelr/apps/datasets.py

@@ -152,7 +152,10 @@ def export(
     label_studio_url: Optional[str] = LABEL_STUDIO_DEFAULT_URL,
     output_dir: Annotated[
         Optional[Path],
-        typer.Option(help="Path to the output directory", file_okay=False),
+        typer.Option(
+            help="Path to the output directory. Only used if the destintation (`to`) is `ultralytics`",
+            file_okay=False,
+        ),
     ] = None,
     dataset_dir: Annotated[
         Optional[Path],
@@ -200,11 +203,18 @@ def export(
             help="Use the AWS S3 cache for image downloads instead of images.openfoodfacts.org, "
             "it is ignored if the export format is not Ultralytics"
         ),
-    ] = True,
+    ] = False,
     merge_labels: Annotated[
         bool,
         typer.Option(help="Merge multiple labels into a single label"),
     ] = False,
+    revision: Annotated[
+        str,
+        typer.Option(
+            help="Revision (branch, tag or commit) for the Hugging Face Datasets repository. "
+            "Only used when importing from or exporting to Hugging Face Datasets."
+        ),
+    ] = "main",
 ):
     """Export Label Studio annotation, either to Hugging Face Datasets or
     local files (ultralytics format)."""
@@ -261,6 +271,7 @@ def export(
                 project_id=typing.cast(int, project_id),
                 merge_labels=merge_labels,
                 use_aws_cache=use_aws_cache,
+                revision=revision,
             )
         elif to == ExportDestination.ultralytics:
             export_from_ls_to_ultralytics_object_detection(
@@ -286,6 +297,7 @@ def export(
                 download_images=download_images,
                 error_raise=error_raise,
                 use_aws_cache=use_aws_cache,
+                revision=revision,
             )
         else:
             raise typer.BadParameter("Unsupported export format")

{labelr-0.6.0 → labelr-0.7.0}/src/labelr/apps/train.py

@@ -6,6 +6,31 @@ from google.cloud import batch_v1
 app = typer.Typer()
 
 
+AVAILABLE_OBJECT_DETECTION_MODELS = [
+    "yolov8n.pt",
+    "yolov8s.pt",
+    "yolov8m.pt",
+    "yolov8l.pt",
+    "yolov8x.pt",
+    "yolov9t.pt",
+    "yolov9s.pt",
+    "yolov9m.pt",
+    "yolov9c.pt",
+    "yolov9e.pt",
+    "yolov10n.pt",
+    "yolov10s.pt",
+    "yolov10m.pt",
+    "yolov10b.pt",
+    "yolov10l.pt",
+    "yolov10x.pt",
+    "yolo11n.pt",
+    "yolo11s.pt",
+    "yolo11m.pt",
+    "yolo11l.pt",
+    "yolo11x.pt",
+]
+
+
 @app.command()
 def train_object_detection(
     wandb_project: str = typer.Option(
@@ -25,9 +50,20 @@ def train_object_detection(
     ),
     epochs: int = typer.Option(100, help="Number of training epochs."),
     imgsz: int = typer.Option(640, help="Size of the image during training."),
-    batch_size: int = typer.Option(64, help="Batch size for training."),
+    batch: int = typer.Option(64, help="Batch size for training."),
+    model_name: str = typer.Option(
+        "yolov8n.pt",
+        help="The YOLO model variant to use for training. "
+        "This should be a valid Ultralytics model name.",
+    ),
 ):
     """Train an object detection model."""
+
+    if model_name not in AVAILABLE_OBJECT_DETECTION_MODELS:
+        raise typer.BadParameter(
+            f"Invalid model name '{model_name}'. Available models are: {', '.join(AVAILABLE_OBJECT_DETECTION_MODELS)}"
+        )
+
     env_variables = {
         "HF_REPO_ID": hf_repo_id,
         "HF_TRAINED_MODEL_REPO_ID": hf_trained_model_repo_id,
@@ -37,8 +73,9 @@ def train_object_detection(
         "WANDB_API_KEY": wandb_api_key,
         "EPOCHS": str(epochs),
         "IMGSZ": str(imgsz),
-        "BATCH_SIZE": str(batch_size),
+        "BATCH_SIZE": str(batch),
         "USE_AWS_IMAGE_CACHE": "False",
+        "YOLO_MODEL_NAME": model_name,
     }
     job_name = "train-yolo-job"
     job_name = job_name + "-" + datetime.datetime.now().strftime("%Y%m%d%H%M%S")

labelr-0.7.0/src/labelr/dataset_features.py

@@ -0,0 +1,31 @@
+import datasets
+from datasets import Features
+from datasets import Image as HFImage
+
+# dataset features for predictions.parquet used in evaluation and visualization
+OBJECT_DETECTION_DS_PREDICTION_FEATURES = Features(
+    {
+        "image": HFImage(),
+        "image_with_prediction": HFImage(),
+        "image_id": datasets.Value("string"),
+        "detected": {
+            "bbox": datasets.Sequence(datasets.Sequence(datasets.Value("float32"))),
+            "category_id": datasets.Sequence(datasets.Value("int64")),
+            "category_name": datasets.Sequence(datasets.Value("string")),
+            "confidence": datasets.Sequence(datasets.Value("float32")),
+        },
+        "split": datasets.Value("string"),
+        "width": datasets.Value("int64"),
+        "height": datasets.Value("int64"),
+        "meta": {
+            "barcode": datasets.Value("string"),
+            "off_image_id": datasets.Value("string"),
+            "image_url": datasets.Value("string"),
+        },
+        "objects": {
+            "bbox": datasets.Sequence(datasets.Sequence(datasets.Value("float32"))),
+            "category_id": datasets.Sequence(datasets.Value("int64")),
+            "category_name": datasets.Sequence(datasets.Value("string")),
+        },
+    }
+)

{labelr-0.6.0 → labelr-0.7.0}/src/labelr/export.py

@@ -36,11 +36,18 @@ def export_from_ls_to_hf_object_detection(
     project_id: int,
     merge_labels: bool = False,
     use_aws_cache: bool = True,
+    revision: str = "main",
 ):
     if merge_labels:
         label_names = ["object"]
 
-    logger.info("Project ID: %d, label names: %s", project_id, label_names)
+    logger.info(
+        "Project ID: %d, label names: %s, repo_id: %s, revision: %s",
+        project_id,
+        label_names,
+        repo_id,
+        revision,
+    )
 
     for split in ["train", "val"]:
         logger.info("Processing split: %s", split)
@@ -70,7 +77,13 @@ def export_from_ls_to_hf_object_detection(
                 functools.partial(_pickle_sample_generator, tmp_dir),
                 features=HF_DS_OBJECT_DETECTION_FEATURES,
             )
-            hf_ds.push_to_hub(repo_id, split=split)
+            hf_ds.push_to_hub(
+                repo_id,
+                split=split,
+                revision=revision,
+                # Create a PR if not pushing to main branch
+                create_pr=revision != "main",
+            )
 
 
 def export_from_ls_to_ultralytics_object_detection(
@@ -234,7 +247,7 @@ def export_from_hf_to_ultralytics_object_detection(
             is True. Defaults to True.
         revision (str): The dataset revision to load. Defaults to 'main'.
     """
-    logger.info("Repo ID: %s", repo_id)
+    logger.info("Repo ID: %s, revision: %s", repo_id, revision)
     ds = datasets.load_dataset(repo_id, revision=revision)
     data_dir = output_dir / "data"
     data_dir.mkdir(parents=True, exist_ok=True)

labelr-0.7.0/src/labelr/utils.py

@@ -0,0 +1,13 @@
+def parse_hf_repo_id(hf_repo_id: str) -> tuple[str, str]:
+    """Parse the repo_id and the revision from a hf_repo_id in the format:
+    `org/repo-name@revision`.
+
+    Returns a tuple (repo_id, revision), with revision = 'main' if it
+    was not provided.
+    """
+    if "@" in hf_repo_id:
+        hf_repo_id, revision = hf_repo_id.split("@", 1)
+    else:
+        revision = "main"
+
+    return hf_repo_id, revision

{labelr-0.6.0 → labelr-0.7.0/src/labelr.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: labelr
-Version: 0.6.0
+Version: 0.7.0
 Summary: A command-line tool to manage labeling tasks with Label Studio.
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
@@ -12,8 +12,11 @@ Requires-Dist: more-itertools>=10.5.0
 Requires-Dist: openfoodfacts>=2.9.0
 Requires-Dist: typer>=0.15.1
 Requires-Dist: google-cloud-batch==0.18.0
+Requires-Dist: huggingface-hub
 Provides-Extra: ultralytics
-Requires-Dist: ultralytics>=8.3.49; extra == "ultralytics"
+Requires-Dist: ultralytics==8.3.223; extra == "ultralytics"
+Provides-Extra: fiftyone
+Requires-Dist: fiftyone~=1.10.0; extra == "fiftyone"
 Dynamic: license-file
 
 # Labelr

{labelr-0.6.0 → labelr-0.7.0}/src/labelr.egg-info/SOURCES.txt

@@ -6,11 +6,13 @@ src/labelr/__main__.py
 src/labelr/annotate.py
 src/labelr/check.py
 src/labelr/config.py
+src/labelr/dataset_features.py
 src/labelr/export.py
 src/labelr/main.py
 src/labelr/project_config.py
 src/labelr/sample.py
 src/labelr/types.py
+src/labelr/utils.py
 src/labelr.egg-info/PKG-INFO
 src/labelr.egg-info/SOURCES.txt
 src/labelr.egg-info/dependency_links.txt

{labelr-0.6.0 → labelr-0.7.0}/src/labelr.egg-info/requires.txt

@@ -5,6 +5,10 @@ more-itertools>=10.5.0
 openfoodfacts>=2.9.0
 typer>=0.15.1
 google-cloud-batch==0.18.0
+huggingface-hub
+
+[fiftyone]
+fiftyone~=1.10.0
 
 [ultralytics]
-ultralytics>=8.3.49
+ultralytics==8.3.223