0

I'm trying to make image detection model with 500 images. I just tried 128 epochs which took about 3 hours of training. I like the way it is working but I want to train more to get close to perfect because it has some difficult time to recognize with different background color/environment/surroundings.

The question is, if I want to simply add more images on the same model, how can i do that? Is there a way that I can load custom trained model? Like can I take the best.py output and paste it to command then start training with more image/label file?

Since it takes so long with 500 images I can't imagine how long it will take with 3,000 images. I want to continue training model that has already done trained.

Thank you for your helps...

This is the line that I am using: yolo task=detect mode=train epochs=128 data=data_custom.yaml model=yolov8m.pt imgsz=640 batch=11 patience=64

And this is the folder with best.py: C:\Users\musti\OneDrive\Desktop\TheCoding\YOLOV8\runs\detect\train2\weights

Muto
  • 1
  • 3

1 Answers1

0

I somehow understood what to do. I will explain as basic as possible for who doesn't know coding like me;

1-) Go to weights folder and take best.py/last.py whatever you like

2-) Paste it in to main folder

3-) Go to your cmd and just change the name of model to your pt file like this;

I am using this code to start yolo

yolo task=detect mode=train epochs=128 data=data_custom.yaml model=yolov8m.pt imgsz=640 batch=11 patience=64

And after changing the name of best.pt to yolov8m_custom_train1.pt I changed my code to this

yolo task=detect mode=train epochs=128 data=data_custom.yaml model=yolov8m_custom_train1.pt imgsz=640 batch=11 patience=64

4-) Just press enter and see if it worked for you. If it does not sorry but I can't help either.

Muto
  • 1
  • 3