Ultralytics

🌟 Summary
The YOLOv8 v8.3.77 release introduces a significant performance optimization for ONNX Runtime segmentation models, as well as essential compatibility enhancements and minor fixes. 🚀

---

📊 Key Changes
- **🚀 YOLOv8-Segment Optimization (ONNX Runtime)**
- Post-processing was drastically improved for both GPU (91.7% faster) and CPU (58.9% faster), resulting in a total inference speedup of up to 32.4%.

- **🔧 Optional `thop` Dependency Support**
- Made the `thop` library optional by handling its absence gracefully to avoid errors in environments lacking it.

- **📂 ONNX Export Improvements**
- Streamlined ONNX dynamic model export logic by revising type handling, ensuring better reliability and maintainability.

---

🎯 Purpose & Impact
- **Faster and More Efficient Inference ⚡**
- The optimization of YOLOv8-Segment ONNX Runtime reduces latency significantly, improving user experiences in deployment scenarios where real-time performance is essential.

- **Increased Compatibility with Minimal Setups 🤝**
- By making `thop` optional, the release ensures broader support for systems, including lightweight environments like Conda setups, enhancing user flexibility.

- **Improved Developer Experience 🛠️**
- Simplified export logic and code maintainability ensures a more robust development and debugging process for ONNX users.

These updates collectively enhance usability, efficiency, and reliability for YOLOv8 users across diverse applications. 🎉

What's Changed
* Fix dynamic export with YOLO World by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19304
* Revert "Fix dynamic export with YOLO World" by Laughing-q in https://github.com/ultralytics/ultralytics/pull/19308
* Allow missing `thop` package by glenn-jocher in https://github.com/ultralytics/ultralytics/pull/19314
* `ultralytics 8.3.77` faster YOLOv8-Segment ONNX Runtime example by AdnanEkici in https://github.com/ultralytics/ultralytics/pull/19312

New Contributors
* AdnanEkici made their first contribution in https://github.com/ultralytics/ultralytics/pull/19312

**Full Changelog**: https://github.com/ultralytics/ultralytics/compare/v8.3.76...v8.3.77

🌟 Summary
The release of Ultralytics v8.3.76 introduces improved dynamic batch inference for ONNX models with NMS export, a better object tracking experience, and various code and documentation enhancements. 🚀

---

📊 Key Changes
- **Dynamic Batch Improvements**:
- Solved issues with `dynamic=True` and `nms=True` where the batch size was fixed at export.
- Enabled dynamic input handling by introducing padding for unmatched batch sizes during ONNX exports.

- **Tracking Enhancements**:
- Addressed errors when processing Torch tensors in `model.track()`.
- Improved integration of original input images with trackers for accuracy.

- **Performance Accuracy**:
- Fixed GPU memory conversion errors for logging VRAM usage to ensure accurate reporting.

- **Documentation Updates**:
- Standardized formatting in documentation for better consistency.
- Enhanced examples for interpreting prediction results across detection, pose, segmentation, and more.

- **Other Code Refinements**:
- Addressed layer miscount in logging by ensuring layers with no parameters are also displayed.
- Enhanced GitHub issue templates for clearer differentiation between bug reports and feature requests.

---

🎯 Purpose & Impact
- 🛠 **Improved Model Deployment**: Dynamic padding during export ensures robust handling of varying batch sizes while maintaining compatibility with ONNX workflows.
- 🎥 **Better Tracking**: Smoother operation for streamed data and enhanced consistency in object tracking results benefit both developers and end-users.
- 📋 **Accurate Logging**: Correct VRAM usage metrics improve debugging and resource optimization.
- 📚 **Developer Friendliness**: Updated docs and examples make it easier for users to understand and utilize prediction results effectively.
- 🚀 **Efficiency Boost**: Code tweaks and fixes culminate in faster, more accurate model handling without disruptions.

This release addresses several community-reported issues, focusing on operational accuracy and usability across export, tracking, and development workflows! 🙌

What's Changed
* Initialize `model_name` attribute by LoveAndHope-dev in https://github.com/ultralytics/ultralytics/pull/19224
* Update results.boxes docs: boxes.id may be None by shankangke in https://github.com/ultralytics/ultralytics/pull/19227
* Fix bytes to GB conversion for logged VRAM usage by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19254
* Fix memory conversion by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19256
* Use new "Issue Type" in templates by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19257
* Add https://youtu.be/im7xBCnPURg to docs by RizwanMunawar in https://github.com/ultralytics/ultralytics/pull/19265
* Support CoreML NMS export for Segment, Pose and OBB by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19173
* Fix layer count; show layers with no params in detailed log by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19202
* Standardize `str` formatting in docs by lakshanthad in https://github.com/ultralytics/ultralytics/pull/19276
* Add detailed usage with demos to reCamera doc by lakshanthad in https://github.com/ultralytics/ultralytics/pull/19275
* Add examples showing how to use `result` for all tasks by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19282
* Update `model_data.py` by RizwanMunawar in https://github.com/ultralytics/ultralytics/pull/19267
* Revert "Support CoreML NMS export for Segment, Pose and OBB" by glenn-jocher in https://github.com/ultralytics/ultralytics/pull/19273
* Fix error with `torch` tensor input in `model.track()` by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19278
* `ultralytics 8.3.76` fix `dynamic` batch inference with NMS export by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19249

New Contributors
* LoveAndHope-dev made their first contribution in https://github.com/ultralytics/ultralytics/pull/19224

**Full Changelog**: https://github.com/ultralytics/ultralytics/compare/v8.3.75...v8.3.76

🌟 Summary
The v8.3.75 release includes robust updates for improved model export compatibility, user experience, and error handling across platforms, alongside enhanced documentation and integration refinements. 🚀

---

📊 Key Changes
- **Enhanced CometML Integration**:
- Transitioned to the new `comet_ml.start()` API for smoother experiment handling.
- Deprecated the `COMET_MODE` variable, introducing `COMET_START_ONLINE` for consistency.

- **Export Function Updates**:
- **Protobuf Dependency**: Added support for `protobuf>=5` for TensorFlow and TFLite exports, resolving compatibility issues.
- **Edge TPU and TF.js**: Addressed platform-specific limitations for ARM64 and Linux exports to prevent unsupported configuration errors.

- **Documentation Improvements**:
- Updated SAM auto-annotation, YOLOv8, and export format descriptions for clarity.
- Redesigned inference examples to use accessible publicly hosted image URLs.

- **New CLI Solutions**:
- Introduced practical use cases, including object counting, workout monitoring, queue analysis, and browser-based inference with Streamlit.

- **Benchmarking Added**:
- Include new comparative performance metrics for popular object detection models like Gold-YOLO, YOLO-NAS, RTDETRv3, etc.

- **Windows-Specific Fix**:
- Resolved an async file write bug to improve caching reliability on Windows systems.

- **Improved Timing Precision**:
- Switched to `time.perf_counter()` for latency measurements, ensuring greater precision during benchmarking.

---

🎯 Purpose & Impact
- **Improved Experiment Tracking**:
- Seamless CometML integration provides better environment consistency and logging during training processes.

- **Enhanced Export Reliability**:
- Future-proofs TensorFlow and TFLite workflows while providing early error detection for ARM64/Linux users.

- **Streamlined User Experience**:
- Updated documentation and example consistency ensure clarity, especially for beginners, minimizing friction during model setup and usage.

- **Greater Platform Support**:
- Addressed critical Windows and platform-specific export edge cases, enhancing cross-platform usability.

- **Better Model Insights**:
- Added benchmarks empower users to make informed decisions about which object detection models to implement based on accuracy, speed, and computational cost.

This release focuses heavily on improving reliability, usability, and documentation quality while resolving critical bugs and adding more tools for diverse real-world applications.

What's Changed
* Auto-annotate and SAM docs update by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19156
* Switch to `perf_counter()` for latency measurement by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19177
* Force protobuf>=5 for SavedModel export by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19206
* Fix Docker QEMU issues while building JetPack 6 Dockerfile by lakshanthad in https://github.com/ultralytics/ultralytics/pull/19216
* Fix `bus.jpg` path in `predict.md` by RizwanMunawar in https://github.com/ultralytics/ultralytics/pull/19203
* Update NMS description on export-args.md by Buligon in https://github.com/ultralytics/ultralytics/pull/19211
* Add NMS related args to export-table.md by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19215
* Add Docs models benchmark by Laughing-q in https://github.com/ultralytics/ultralytics/pull/19176
* Tasks Docs updates by LexBarou in https://github.com/ultralytics/ultralytics/pull/19181
* YOLOv8 Docs updates by LexBarou in https://github.com/ultralytics/ultralytics/pull/19182
* Add Solutions CLI usage in `quickstart.md` by RizwanMunawar in https://github.com/ultralytics/ultralytics/pull/19160
* Fix `edgetpu` and `tfjs` exports for `arm64` Linux by lakshanthad in https://github.com/ultralytics/ultralytics/pull/19154
* Fix windows async np.save bug by eric80739 in https://github.com/ultralytics/ultralytics/pull/19218
* Fix `print()` for ConfusionMatrix for Classify task by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19169
* Fix updating of best epoch during early stopping by vfcosta in https://github.com/ultralytics/ultralytics/pull/19164
* `ultralytics 8.3.75` Comet update to new `comet_ml.start()` API by yaricom in https://github.com/ultralytics/ultralytics/pull/19187

New Contributors
* vfcosta made their first contribution in https://github.com/ultralytics/ultralytics/pull/19164
* eric80739 made their first contribution in https://github.com/ultralytics/ultralytics/pull/19218

**Full Changelog**: https://github.com/ultralytics/ultralytics/compare/v8.3.74...v8.3.75

---

📊 Key Changes
- 🔧 **Fixed Ray Tune Callback Issues**: Replaced deprecated `ray.tune.is_session_enabled()` with `ray.train._internal.session.get_session()` ensuring compatibility with latest Ray versions.
- 🛠 **Enhanced Deterministic Training Control**: Added `unset_deterministic()` to handle environment changes, and prevent unnecessary CUDA warnings.
- 🖼 **PIL Image Support in `plot()`**: Allowed direct return of PIL images with `annotator.im`, improving compatibility with PIL workflows.
- 🚀 **Improved Export Flexibility**: Adjusted `model.export()` to take a `data` parameter while simplifying `predict()` calls.
- 🐳 **Optimized Docker Workflow**: Improved Docker token authentication and switched to `docker build` for better stability and security.
- ✅ **Streamlined Benchmarking**: Cleaned dataset and metric assignments in benchmarking to avoid redundancy and improve reliability.

---

🎯 Purpose & Impact
- 🚀 **Greater Compatibility**: Seamless integration with the latest versions of Ray ensures that errors linked to deprecated methods are resolved.
- ⚡ **Workflow Flexibility**: Managing deterministic settings dynamically boosts training adaptability while cleaning up workflow logs.
- 📸 **Visualization Improvements**: Returning PIL images directly simplifies further processing in pipelines dependent on image outputs.
- 🛠️ **User-Friendly Model Exports**: Configurable export makes model usage and testing more straightforward for developers.
- 🔒 **Stronger Security**: Docker workflow improvements enhance authentication security, benefitting advanced build setups.
- ✅ **Clarity in Development**: Benchmark logic cleanup minimizes confusion and potential errors, improving developer experience.

This version is packed with incremental improvements, making model training, testing, and deployment smoother and more user-friendly while preparing Ultralytics for the future. 🎉

What's Changed
* Fix docker.yml by glenn-jocher in https://github.com/ultralytics/ultralytics/pull/19125
* Fix missing data warning and undefined variables by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19124
* Fix missing data.yaml error on int8 export by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19128
* Return PIL image if `pil=True` by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19146
* Unset CUBLAS_WORKSPACE_CONFIG for non-deterministic training and inference by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19138
* `ultralytics 8.3.74` Fix Ray Tune callback error by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19144


**Full Changelog**: https://github.com/ultralytics/ultralytics/compare/v8.3.73...v8.3.74

🌟 Summary
The Ultralytics `v8.3.73` release focuses on enhancing containerization workflows, updating library dependencies, improving documentation, and refining the development process. 🚀

---

📊 Key Changes
- **Containerization Enhancements**:
- Added support for publishing Docker images to both **GitHub Container Registry (GHCR)** and **Docker Hub** with rich metadata for better usability. 🐋
- Removed Ubuntu 24.04 ARM in CI workflows for streamlined testing.
- **Dependency and Platform Updates**:
- Updated NVIDIA Jetson support with **PyTorch 2.2.0** and **Torchvision 0.17.2** for improved compatibility and performance. 🤖
- Removed the `beautifulsoup4` dependency, cleaning up the development environment. 🧹
- **Code Refactoring**:
- Improved SQL result export by simplifying insertion logic and fixing potential issues with empty results.
- Enhanced type hinting for better code clarity.
- **Documentation and Tutorial Updates**:
- Added an embedded YouTube tutorial on *Package Segmentation* in the documentation. 🎥✨

---

🎯 Purpose & Impact
- **Containerization Accessibility**:
- Publishing images to both Docker Hub and GHCR ensures users have multiple options for pulling images, increasing global availability and reducing friction. 🌍
- The inclusion of detailed metadata in Docker images improves clarity for end-users.
- **Better Hardware and Development Support**:
- NVIDIA Jetson users benefit from *newer library versions* for seamless deployment and better model performance.
- Leaner development environments reduce installation times and maintenance burdens.
- **Improved Learning Resources**:
- The YouTube tutorial enriches the documentation and aids new and existing users in understanding package segmentation workflows visually. 📚👩‍💻

---

TL;DR: This version updates Docker container workflows, improves NVIDIA Jetson compatibility, cleans up dev dependencies, and enhances user education through new video tutorials. 🚀💡

What's Changed
* Remove `beautifulsoup4<=4.12.3` pin by Laughing-q in https://github.com/ultralytics/ultralytics/pull/19103
* Update JetPack 5 `torch` and `torchvision` packages by lakshanthad in https://github.com/ultralytics/ultralytics/pull/19098
* Minor `Results.to_sql` cleanup by Laughing-q in https://github.com/ultralytics/ultralytics/pull/19081
* Add https://youtu.be/im7xBCnPURg to docs by RizwanMunawar in https://github.com/ultralytics/ultralytics/pull/19115
* `ultralytics 8.3.73` GitHub Container Registry Images at `ghcr.io` by glenn-jocher in https://github.com/ultralytics/ultralytics/pull/19114


**Full Changelog**: https://github.com/ultralytics/ultralytics/compare/v8.3.72...v8.3.73

🌟 Summary
The `v8.3.72` release focuses on enhancing NVIDIA Jetson DLA (Deep Learning Accelerator) core compatibility for inference, improving export documentation, and resolving minor inefficiencies and errors for broader usability and smoother performance. 🚀

📊 Key Changes
- **Enhanced NVIDIA Jetson DLA Support**:
- Introduced explicit control of DLA core selection (`dla:0`/`dla:1`) during TensorRT export and inference.
- Added detailed documentation of NVIDIA Jetson DLA device specifications (core count, frequency, etc.).
- Fixed metadata handling for DLA-specific inference settings.
- **Export Documentation Overhaul**:
- Added detailed argument tables for all model export formats (e.g., ONNX, TensorRT, CoreML), improving clarity on custom export options such as half-precision (FP16), INT8 quantization, and dynamic input sizes.
- **Optimized `seg_bbox` Rendering**:
- Refined label handling logic in the plotting utility, reducing unnecessary operations if a label is absent, slightly improving performance.
- **Bug Fixes**:
- Resolved an issue with missing `nc` attributes during NMS export, improving reliability in multi-GPU or custom training setups.
- **Documentation Updates**:
- Enhanced Crack Segmentation Dataset resources with direct Colab integration, a tutorial notebook, and a demo video for easier onboarding.

🎯 Purpose & Impact
- **Improved Compatibility**: The NVIDIA Jetson DLA improvements ensure that edge devices benefit from seamless inference setups, enabling accelerated performance with reduced bottlenecks. Ideal for IoT and edge AI devices. 🖥️✨
- **Simplified Export Process**: The new export argument tables demystify complex configurations, empowering users to adapt models for their specific hardware or workflows more easily. 📦🔧
- **Performance Benefits**: Minor optimizations ensure faster runtime efficiency, especially for visualization and plotting tasks where unnecessary computations are avoided. ⚡
- **Enhanced Reliability**: Fixes like handling missing `nc` attributes and metadata improve model robustness, particularly in advanced user scenarios (e.g., multi-GPU setups, custom models). ✅
- **Streamlined Learning Experience**: The improved Crack Segmentation training resources lower the barrier to entry for researchers in infrastructure and transportation safety fields. 🛠️🚗

This release represents a strong push for enhanced edge device support, better export usability, and overall reliability improvements while empowering both beginners and advanced users. 🎉

What's Changed
* Optimize `seg_bbox` calculations by RizwanMunawar in https://github.com/ultralytics/ultralytics/pull/19056
* Resolve warnings by glenn-jocher in https://github.com/ultralytics/ultralytics/pull/19073
* Add https://youtu.be/C4mc40YKm-g and notebook badge in docs by RizwanMunawar in https://github.com/ultralytics/ultralytics/pull/19086
* Add Export Arguments tables to all Export docs by lakshanthad in https://github.com/ultralytics/ultralytics/pull/18952
* Fix missing nc attribute error on NMS export by Y-T-G in https://github.com/ultralytics/ultralytics/pull/19083
* Replace `beautifulsoup4` pin with `mkdocs-ultralytics-plugin>=0.1.17` by Laughing-q in https://github.com/ultralytics/ultralytics/pull/19085
* `ultralytics 8.3.72` Fix NVIDIA Jetson DLA core support for DLA inference by Laughing-q in https://github.com/ultralytics/ultralytics/pull/19078


**Full Changelog**: https://github.com/ultralytics/ultralytics/compare/v8.3.71...v8.3.72