What's New in YOLOv8 | Model Deep Dive

On January 10th, 2023, Ultralytics launched YOLOv8, a new state-of-the-art model for object detection and image segmentation. YOLOv8 also has out-of-the-box support for image classification.

Join us in this video to dive deep into what YOLOv8 is, how it works, and how it compares to previous YOLO models.

Resources

[shanep]

Great job as usual. Very informative! CLI is clutch, can't wait for the roboflow ultralytics hub for V8 aswell!

[israelgaytan]

Hi, I really enjoy your contributions, thank you very much for that.
I would like to ask, with this model how can I save the detections made in an inference in a text file? the --save-txt command does not work and I see that the detect.py file is not used.
I would be very grateful for your answer
Best regards!

[hajerbettayeb]

Thank you for sharing. I have question about results of YOLOv8 model, after the training of the model it results in a 3-dimensional confusion matrix taking the background as a class knowing that I have a binary classification my project is classification of preforms whether it is defect or not. What can be the raisaon of appearance of this class "backgroud" and how I can solve it ? if you help me I would be grateful.

[nkirukauzuegbunam]

is the architecture very different from yolov7? would you have a comparison of yolov5, 7, 8?

[TheBradleydwyer]

Where can I try the basketball model myself?

[frankoptis]

"Python better than C"..that was the moment he knew he up ;-)

[markuskreutz]

"obviously, Python is better than C"

Should I assume the credibility of the rest of the video and the roboflow-blog to be similarly bad, or was this a one-time blunder?

[AlbertoZolezzi-bvpd]

"Python better than C"..please no :)