diff --git a/README.md b/README.md index 646cbd0..a87bb72 100644 --- a/README.md +++ b/README.md @@ -103,6 +103,28 @@ Each plugin entry below includes the exact copy-paste install command. After ins +- [YOLO object detection](plugins/yolo_object_detection/) + Runs YOLO inference and adds bounding box annotations to unlabeled images. + +
+ Details + + Uses [Ultralytics YOLO](https://docs.ultralytics.com/) models for object detection auto-labeling. + Supports any Ultralytics model name or a path to a custom checkpoint. + + - Scope: single image or images in the current view + - Input: YOLO model name or local path to a YOLO checkpoint + - Output: object detection annotations + - Labels: class labels are read from the loaded model and created in the + dataset if they do not exist yet + - Recommended models: + `yolov8n.pt` for speed, `yolov8s.pt` or `yolov8m.pt` for better accuracy + - Maintainer: Lightly + - Install: + `pip install git+https://github.com/lightly-ai/lightly-studio-plugins.git#subdirectory=plugins/yolo_object_detection/` + +
+ - [KITTI object detection export](plugins/kitti_export_object_detection/) Exports KITTI object-detection label files. diff --git a/plugins.toml b/plugins.toml index d39bd7b..bbcdc98 100644 --- a/plugins.toml +++ b/plugins.toml @@ -22,6 +22,14 @@ source = "local:plugins/lightly_train_object_detection_inference" maintainer = "lightly" tags = ["auto-labeling", "object-detection", "inference"] +[[plugins]] +id = "lightly_plugins_yolo_object_detection" +name = "YOLO Object Detection" +description = "Runs YOLO inference and adds bounding box annotations to a single image or the current filtered image view" +source = "local:plugins/yolo_object_detection" +maintainer = "lightly" +tags = ["auto-labeling", "object-detection", "inference"] + [[plugins]] id = "lightly_plugins_kitti_export_object_detection" name = "KITTI object detection export" diff --git a/plugins/yolo_object_detection/LICENSE b/plugins/yolo_object_detection/LICENSE new file mode 100644 index 0000000..f49a4e1 --- /dev/null +++ b/plugins/yolo_object_detection/LICENSE @@ -0,0 +1,201 @@ + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/plugins/yolo_object_detection/Makefile b/plugins/yolo_object_detection/Makefile new file mode 100644 index 0000000..394c786 --- /dev/null +++ b/plugins/yolo_object_detection/Makefile @@ -0,0 +1,13 @@ +.PHONY: install format type-check + +install: + uv venv + uv pip install -r ../../dev-requirements.txt + uv pip install -e . + +format: + uv run ruff format . + uv run ruff check --fix . + +type-check: + uv run mypy --config-file ../../mypy.ini . diff --git a/plugins/yolo_object_detection/README.md b/plugins/yolo_object_detection/README.md new file mode 100644 index 0000000..a18d3b4 --- /dev/null +++ b/plugins/yolo_object_detection/README.md @@ -0,0 +1,25 @@ +# YOLO Object Detection Plugin + +Auto-labeling with [Ultralytics YOLO](https://docs.ultralytics.com/) models. Runs YOLO inference and adds bounding box annotations to images in Lightly Studio. + +## Setup + +### Install the plugin + +```bash +uv pip install "git+https://github.com/lightly-ai/lightly-studio-plugins.git#subdirectory=plugins/yolo_object_detection/" +``` + +## Parameters + +| Parameter | Type | Default | Description | +|---|---|---|---| +| `model_path` | string | `"yolov8n.pt"` | YOLO model weights path or Ultralytics model name (e.g. `yolov8s.pt`, `yolov8m.pt`, `/path/to/custom.pt`) | +| `confidence` | float | `0.25` | Minimum confidence threshold for keeping a prediction | +| `annotation_source` | string | `"yolo_auto_label__{model_path}"` | Target annotation source name where predictions will be stored | + +## Notes + +- Labels are read from the loaded model and created in the dataset if they do not exist yet. +- Annotations are stored in a collection named `yolo_auto_label__{model_path}` by default, configurable via `annotation_source`. +- Ultralytics model weights are downloaded automatically on first use. diff --git a/plugins/yolo_object_detection/pyproject.toml b/plugins/yolo_object_detection/pyproject.toml new file mode 100644 index 0000000..e8f7ef8 --- /dev/null +++ b/plugins/yolo_object_detection/pyproject.toml @@ -0,0 +1,20 @@ +[project] +name = "lightly_plugins_yolo_object_detection" +version = "0.1.0" +description = "YOLO inference operator for object detection auto-labeling" +requires-python = ">=3.9" +dependencies = [ + "lightly_studio>=1.0.0", + "sqlmodel", + "ultralytics", +] + +[project.entry-points."lightly_studio.plugins"] +yolo_object_detection = "lightly_plugins_yolo_object_detection.operator:YoloObjectDetectionOperator" + +[build-system] +requires = ["hatchling"] +build-backend = "hatchling.build" + +[tool.hatch.build.targets.wheel] +packages = ["src/lightly_plugins_yolo_object_detection"] diff --git a/plugins/yolo_object_detection/src/lightly_plugins_yolo_object_detection/__init__.py b/plugins/yolo_object_detection/src/lightly_plugins_yolo_object_detection/__init__.py new file mode 100644 index 0000000..61fdb3a --- /dev/null +++ b/plugins/yolo_object_detection/src/lightly_plugins_yolo_object_detection/__init__.py @@ -0,0 +1 @@ +"""YOLO object detection plugin for Lightly Studio.""" diff --git a/plugins/yolo_object_detection/src/lightly_plugins_yolo_object_detection/operator.py b/plugins/yolo_object_detection/src/lightly_plugins_yolo_object_detection/operator.py new file mode 100644 index 0000000..e2a532f --- /dev/null +++ b/plugins/yolo_object_detection/src/lightly_plugins_yolo_object_detection/operator.py @@ -0,0 +1,232 @@ +"""YOLO inference operator for object detection auto-labeling.""" + +from __future__ import annotations + +import logging +from dataclasses import dataclass +from typing import Any +from uuid import UUID + +from sqlmodel import Session +from ultralytics import YOLO # type: ignore[attr-defined] + +from lightly_studio.models.annotation.annotation_base import ( + AnnotationCreate, + AnnotationType, +) +from lightly_studio.models.annotation_label import AnnotationLabelCreate +from lightly_studio.plugins.base_operator import BaseOperator, OperatorResult +from lightly_studio.plugins.operator_context import ExecutionContext, OperatorScope +from lightly_studio.plugins.parameter import ( + BaseParameter, + FloatParameter, + StringParameter, +) +from lightly_studio.resolvers import ( + annotation_label_resolver, + annotation_resolver, + collection_resolver, + image_resolver, +) +from lightly_studio.resolvers.image_filter import ImageFilter +from lightly_studio.resolvers.sample_resolver.sample_filter import SampleFilter + +logger = logging.getLogger(__name__) + +DEFAULT_MODEL = "yolov8n.pt" +DEFAULT_CONFIDENCE = 0.25 + +PARAM_MODEL = "model_path" +PARAM_CONFIDENCE = "confidence" +PARAM_ANNOTATION_SOURCE = "annotation_source" + +_WRITE_BATCH_SIZE = 100 + + +@dataclass +class YoloObjectDetectionOperator(BaseOperator): + """Runs YOLO inference to auto-label images with bounding box annotations.""" + + name: str = "YOLO Object Detection" + description: str = ( + "Runs YOLO inference and adds bounding box annotations to unlabeled images." + ) + + @property + def parameters(self) -> list[BaseParameter]: + """Return the list of parameters this operator expects.""" + return [ + StringParameter( + name=PARAM_MODEL, + required=True, + default=DEFAULT_MODEL, + description="YOLO model weights path or Ultralytics model name (e.g. yolov8n.pt).", + ), + FloatParameter( + name=PARAM_CONFIDENCE, + required=True, + default=DEFAULT_CONFIDENCE, + description="Minimum confidence threshold for keeping a prediction.", + ), + StringParameter( + name=PARAM_ANNOTATION_SOURCE, + required=False, + description="Target annotation source name where predictions will be stored. Defaults to yolo_auto_label__{model_path}.", + ), + ] + + @property + def supported_scopes(self) -> list[OperatorScope]: + """Return the list of scopes this operator can be triggered from.""" + return [OperatorScope.IMAGE] + + def execute( + self, + *, + session: Session, + context: ExecutionContext, + parameters: dict[str, Any], + ) -> OperatorResult: + """Execute the operator with the given parameters.""" + model_path = str(parameters.get(PARAM_MODEL, DEFAULT_MODEL)) + _annotation_source = parameters.get(PARAM_ANNOTATION_SOURCE) + collection_name = ( + str(_annotation_source).strip() + if _annotation_source is not None and str(_annotation_source).strip() + else f"yolo_auto_label__{model_path}" + ) + confidence = float(parameters.get(PARAM_CONFIDENCE, DEFAULT_CONFIDENCE)) + + if not 0.0 <= confidence <= 1.0: + return OperatorResult( + success=False, + message="confidence must be between 0 and 1", + ) + + try: + model = YOLO(model_path) + except Exception as e: + logger.error("Failed to load YOLO model '%s': %s", model_path, e) + return OperatorResult( + success=False, + message=f"Failed to load YOLO model '{model_path}': {e}", + ) + label_map = _get_or_create_label_map( + session=session, + root_collection_id=context.collection_id, + class_map=model.names, + ) + + context_filter = None + if context.context_filter: + if isinstance(context.context_filter, SampleFilter): + context_filter = ImageFilter(sample_filter=context.context_filter) + elif isinstance(context.context_filter, ImageFilter): + context_filter = context.context_filter + + samples_result = image_resolver.get_all_by_collection_id( + session=session, + collection_id=context.collection_id, + filters=context_filter, + ) + samples = list(samples_result.samples) + if not samples: + return OperatorResult( + success=True, + message="No samples found for current view.", + ) + + annotations_to_create: list[AnnotationCreate] = [] + total_annotations_created = 0 + for i, image_entry in enumerate(samples, start=1): + try: + results = model( + image_entry.file_path_abs, conf=confidence, verbose=False + )[0] + except Exception as e: + logger.error( + "Failed to run inference on '%s': %s", + image_entry.file_path_abs, + e, + ) + return OperatorResult( + success=False, + message=f"Failed to run inference on '{image_entry.file_path_abs}': {e}", + ) + for box in results.boxes: + category_id = int(box.cls) + label_id = label_map.get(category_id) + if label_id is None: + continue + x_center, y_center, w, h = box.xywh[0].tolist() + annotations_to_create.append( + AnnotationCreate( + annotation_label_id=label_id, + annotation_type=AnnotationType.OBJECT_DETECTION, + parent_sample_id=image_entry.sample_id, + x=round(x_center - w / 2), + y=round(y_center - h / 2), + width=max(1, round(w)), + height=max(1, round(h)), + confidence=float(box.conf), + ) + ) + + if i % _WRITE_BATCH_SIZE == 0 and annotations_to_create: + created = annotation_resolver.create_many( + session=session, + parent_collection_id=context.collection_id, + annotations=annotations_to_create, + collection_name=collection_name, + ) + total_annotations_created += len(created) + annotations_to_create = [] + + if annotations_to_create: + created = annotation_resolver.create_many( + session=session, + parent_collection_id=context.collection_id, + annotations=annotations_to_create, + collection_name=collection_name, + ) + total_annotations_created += len(created) + + return OperatorResult( + success=True, + message=f"Auto-labeled {len(samples)} samples with {total_annotations_created} annotations.", + ) + + +def _get_or_create_label_map( + *, + session: Session, + root_collection_id: UUID, + class_map: dict[int, str], +) -> dict[int, UUID]: + """Ensure labels exist for all class names and return {category_id: label_id}.""" + collection = collection_resolver.get_by_id( + session=session, + collection_id=root_collection_id, + ) + if collection is None: + raise ValueError(f"Collection {root_collection_id} doesn't exist") + dataset_id = collection.dataset_id + + label_map: dict[int, UUID] = {} + for category_id, label_name in class_map.items(): + label = annotation_label_resolver.get_by_label_name( + session=session, + dataset_id=dataset_id, + label_name=label_name, + ) + if label is None: + label = annotation_label_resolver.create( + session=session, + label=AnnotationLabelCreate( + dataset_id=dataset_id, + annotation_label_name=label_name, + ), + ) + label_map[category_id] = label.annotation_label_id + + return label_map