Skillnoob comments

Results 104 comments of


                                            Skillnoob

The YOLOv8s model in v8.3 has a different number of parameters compared to v8.2.

The `Detect` head got changed with v11, so the previous v8 models inherited the new head. Its not the "true" yolov8 head anymore, but the current published yolov8 models still...

Publication of video in landing page

I would reccomend you talk to a lawyer about this.

Problem with detection using numpy as an input in YOLO tarined model.

Please share your code

Are there any webcam which offers more than 200 fps and also combine well with python n yolo?

Probably look for raspberry pi compatible cameras, or something like arducam

Thanks for the YOLO-World model integrated by your team, I would like to ask how I should use yolo-world to detect unknown categories in my own dataset, how to divide and make the dataset, and do I need to pre-define all known categories in yaml files?

If you want to detect using custom classes you can set custom prompts for yolo world: https://docs.ultralytics.com/models/yolo-world/#set-prompts

Modification of yolov8

In general I would not recommend modifying the yaml's in any way unless you know what you are doing. If you are aiming for better accuracy I'd rather advise you...

What is the best linux operating system for YoloV8 and the characteristics of my computer?

It doesn't really matter what linux distribution you use, pretty much any is better than windows. Ubuntu is widely used and is easy for beginners.

Hello author, while using OBB to train my dataset, I found that the tilted boxes in the validation set images and training set images after training did not match. There were cases where the angles were skewed, and during my inference, the detection boxes were completely different from what I labeled

What is your training code

Hello author, while using OBB to train my dataset, I found that the tilted boxes in the validation set images and training set images after training did not match. There were cases where the angles were skewed, and during my inference, the detection boxes were completely different from what I labeled

@yxl23 you ran validation on a yaml. Not your actual model. You need to supply your model file to `YOLO('model.pt')`. `model=...` is not a valid argument for `val(...)`.

Hello author, while using OBB to train my dataset, I found that the tilted boxes in the validation set images and training set images after training did not match. There were cases where the angles were skewed, and during my inference, the detection boxes were completely different from what I labeled

@Y-T-G Can you take a look at this? I'm unsure how to solve this.