Resume training after training with fraction

BurhanQ · February 17, 2025, 11:46pm

The only arguments that can be overridden during resume are:

ultralytics/engine/trainer.py

7397aa707


      
          for k in (
              "imgsz",
              "batch",
              "device",
              "close_mosaic",
          ):  # allow arg updates to reduce memory or update device on resume
              if k in overrides:
                  setattr(self.args, k, overrides[k])

So your change in fraction will be ignored. You would need to (and should) start a new training sessions anyhow if you want to increase the samples to use.

Topic		Replies	Views
Ultralytics YOLOv11 QAT YOLO yolo , question , code	9	256	April 10, 2025
Changing the Loss Function in pretrained models YOLO question , support	3	595	January 30, 2025
YOLO 12 Id'ing images not on my list Support yolo , question , support	15	71	April 1, 2025
Need Help with 1:1 Image Resizing During Training on YOLOv8 Discussion yolov8 , code	3	1396	August 27, 2024
incremental training yolov8 Support question	1	382	September 16, 2024

Resume training after training with fraction

Related topics