YOLOv5 Just Got Stronger in v6.1!

Ultralytics is excited to announce the latest developments in our flagship YOLO (You Only Look Once) technology. With the YOLOv5 v6.1 release, we've fine-tuned our architecture to enhance simplicity, speed, and strength. Our last release in October 2021 laid the groundwork for these advancements, and now we're proud to present these updates that improve YOLO's usability and performance.

Important Updates#

Here are the key enhancements that you'll find in YOLOv5 v6.1:

• TensorRT support: TensorRT export, inference, and validation using python export.py --include engine (#5699 by @imyhxy). This is a significant milestone as NVIDIA's TensorRT is a high-performance deep learning inference optimizer and runtime that delivers low-latency, high-throughput for deep learning applications.
• TensorFlow Edge TPU support ⭐ NEW: Edge TPU export for Google Coral devices using python export.py --include edgetpu (#3630 by @zldrobit). Paired with the smaller YOLOv5n (1.9M params) model introduced in v6.0, which exports to a mere 2.1 MB INT8 size, this is particularly ideal for ultralight mobile solutions.
• OpenVINO support: OpenVINO export using python export.py --include openvino. With OpenVINO, models can now harness the full power of Intel CPUs and integrated GPUs for a versatile array of applications (#6057 by @glenn-jocher).
• Export Benchmarks: We have introduced a new benchmarking tool to assess mAP (Mean Average Precision) and speed across all YOLOv5 export formats with python utils/benchmarks.py --weights yolov5s.pt. Currently operating on CPUs, we plan to extend this to include GPU benchmarks in future updates (#6613 by @glenn-jocher).
• Hyperparameters: There has been a minor yet crucial adjustment to our hyperparameters - in hyp-scratch-large.yaml the learning rate factor (lrf) has been reduced from 0.2 to 0.1 (#6525 by @glenn-jocher).
• Training: The default Learning Rate (LR) scheduler has been updated to one-cycle linear, replacing the previous one-cycle with cosine, for improved training results (#6729 by @glenn-jocher).

YOLOv5 now officially works with 11 formats, supporting not just export but also inference with detect.py and PyTorch Hub, and validation to profile mAP and speed:

• ✅ PyTorch
• ✅ TorchScript
• ✅ ONNX
• ✅ OpenVINO
• ✅ TensorRT
• ✅ CoreML
• ✅ TensorFlow SavedModel
• ✅ TensorFlow GraphDef
• ✅ TensorFlow Lite
• ✅ TensorFlow Edge TPU
• ✅ TensorFlow.js

Together for Everyone's AI#

At Ultralytics, we are driven not merely by the desire to lead but by the passion to participate and contribute to the community. The YOLOv5 family has been instrumental in our journey, supporting us through triumphs and challenges alike. This update is a collective triumph, representing the hard work of 271 PRs from 48 contributors. We stand committed to our mission of democratizing AI, making it accessible and operational for everyone.

Join the Vision AI Revolution#

We are continually looking for talent to join our ranks and invite collaborations on our open-source projects. If you're interested in joining our AI team, explore our careers page or consider contributing to YOLOv5.

From AI Enthusiasts to the Most Popular Object Detection of 2022#

This year, our Ultralytics/YOLOv5 repository has achieved a significant milestone by surpassing Joseph Redmon's pjreddie/darknet YOLOv3 in the total number of GitHub stars, now boasting over 22.4k stars. This is a testament to the trust and enthusiasm of the community, and it motivates us to keep pushing the boundaries of Vision AI. We are deeply honored to carry forward the You Only Look Once legacy.

Visit our YOLOv5 GitHub repository for comprehensive details about the new release and join the vibrant community of YOLO object detection enthusiasts.

Experience the Magic of YOLO With No Code#

But there's more! If you're new to Computer Vision or simply prefer a no-code experience, Ultralytics HUB is your gateway. Discover how to harness YOLO and computer vision technology with just a few clicks. Learn more by visiting Ultralytics HUB - Your Doorway to AI and embark on your journey in Computer Vision.