Ultralytics just released YOLOv8, a state-of-the-art model that builds on the success of previous YOLO versions and includes new features and improvements to further increase its performance and versatility. This model is fast, accurate, and easy to use, making it a great choice for a variety of object detection, image segmentation, and image classification tasks.
The recommended installation is by pip install.
Alternatively, clone the project.
See contributing section to know more about contributing to the project vai CLI or a Python API.
YOLOv8 can be further optimized to reduce inference time by over 5x. The acceleration is achieved by compiling the model onto the hardware and applying specific optimization techniques that further boost inference computing with Speedster.
Speedster is an open-source App designed to speed up AI inference in just a few lines of code. The library boosts your model to achieve the maximum acceleration that is physically possible on your hardware. At this link you can find a notebook on how to accelerate YOLOv8.
YOLOv8 comes with two licenses: GPL-3.0 License, and an Enterprise License that provides greater flexibility for commercial product development without the open-source requirements of GPL-3.0.
End of the year, it's time for guessing. Here's a few collections of AI predictions for 2023 from leading VCs and firms.
ChatLLaMA is an opensource library that allows you to create hyper-personalized ChatGPT-like assistants using your own data and the least amount of compute possible.
Ultralytics just released YOLOv8 and I was looking forward to trying it out to see how it performed in inference. So I built a notebook to experiment with different optimization techniques using Speedster.