Can I use my own YOLOv8 model weights with FastSAM ?

[mertikinci]

I have tried to use a trained YOLOv8 models weights with FastSAM but it is raising an error about mismatching. I know you guys working on a fine-tune/train code right now but I was just curious about whether replacing the weights possible or not ?

Thanks for a great work!

[zxDeepDiver]

Maybe the class number is not consistent?

[mertikinci]

my models class number is 4, do I have to make any more adjustments about it ? or do I need to train a model that has a fixed class number ?

[zxDeepDiver]

Generally, it is not suggested to use the model trained for other tasks in this code. Could you directly use you yolov8 codes in your project?

[mertikinci]

thanks for advice and quick responses 💯

[zxDeepDiver]

Hello. We will close this issue first. Feel free to reopen it if you have any questions.