Yolov5: python train.py --resume

Created on 19 Oct 2020  ·  3Comments  ·  Source: ultralytics/yolov5

❔Question

  1. As I continue to train, the mAP stays zero. Why is that?
  2. Suppose that I set the epoch=300 at the beginning, and the training stopped when epoch=100,. Then I wanted to continue the training for 50 times. How to do this?

Additional context

Stale question

Most helpful comment

when you start training with any command your experiment is saved in yolov5/runs/exp.... If your training is interrupted for any reason, the following command will resume your partially completed training from the most recently updated experiment:

python train.py --resume

or from a specific experiment:

python train.py --resume runs/exp17/weights/last.pt

All 3 comments

when you start training with any command your experiment is saved in yolov5/runs/exp.... If your training is interrupted for any reason, the following command will resume your partially completed training from the most recently updated experiment:

python train.py --resume

or from a specific experiment:

python train.py --resume runs/exp17/weights/last.pt

@whoafridi
As I continue to train, the mAP stays zero. Why is that?

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

Was this page helpful?
0 / 5 - 0 ratings