Yolov8 model returned None on inference after training

Question

I am working on a object detection and counting project , i encountered a problem where the model was found to be returning a None object on inference after training it for 100 epochs in a dataset of 600(300 images augmented) images. I used roboflow for annotation and augmentation. The object i am trying to focus is a motorcycle/scooter with people on it. I used YoloV8 nano algorithm.

I was expecting it to produce bounding box values as results but it returned None. Is it because the image set(~600) was too small ?? or the epoch ??

Most probably the problem is with the config file. Your training config and inference config must be the same except for a few changes. — Rukon, Jul 30 '23 at 06:26

Manish Prajapati · Answer 1 · 2023-07-31T19:42:03.387

0

please check your code again, some time it happens due to some coding error. Note that Yolo v8 return the array which contain output information. it basically contain bounding box information, label and confidence score. go through with following link for better understanding to solve your problem.

https://inside-machinelearning.com/en/yolov8-how-to-use/

edited Jul 31 '23 at 19:42

answered Jul 31 '23 at 19:40

Manish Prajapati

3
2

Your answer could be improved with additional supporting information. Please [edit] to add further details, such as citations or documentation, so that others can confirm that your answer is correct. You can find more information on how to write good answers [in the help center](/help/how-to-answer). – Community Aug 11 '23 at 18:49

Yolov8 model returned None on inference after training

1 Answers1