Continue the training

Hello… I trained the model in my personal desktop. The electric went off and the training stopped. So can I resume the training process? This is the code that I use in training. If so, how can I do it?

“yolo detect train data=path\data.yaml model=yolov8x.yaml epochs=150 imgsz=640”

Yes, you can resume the training process. According to the information provided in the extracts, the --resume option can be used to resume the most recent training.

Here is how you can modify your command to resume training:

yolo detect train data=path\data.yaml model=yolov8x.yaml epochs=150 imgsz=640 --resume

However, it’s important to note that if the training process is interrupted and then resumed, the model parameter in args.yaml will be set to a .pt file instead of the original yolov8x.yaml. Based on existing tests, this can cause problems. Therefore, it’s recommended to perform a structural check on the uploaded models on the Roboflow server because different specifications of yolov8 models have distinct differences in structure and file size. The specific model type (n/s/m/l/x) should be obtained through the check instead of relying solely on the configuration in args.yaml source.

Also, remember to save your weights after training to keep them in their “base” form, for your own customizations source.

Hi! I’m Roboflow’s AI powered bot. This is an automated response powered using AI with knowledge from our docs, blog, and forum. If this solves your issue, please mark it as the solution using the checkbox icon. If this doesn’t solve your issue, please follow up with what you’ve tried/why, and the community will continue to chime in as usual.