Replies: 6 comments 4 replies
-
@ameicler could you expand on your use case a little? Maybe @AyushExel can help you out. |
Beta Was this translation helpful? Give feedback.
-
Sure. I would like to train object detection models with medical images and therefore not have any images stored/saved/sent to wandb platform (i.e. need to disable the boundingboxdebugger feature and maybe other). Is there an easy way to do so? |
Beta Was this translation helpful? Give feedback.
-
@ameicler hey. You can set the @glenn-jocher on that note, do you think having a flag similar to |
Beta Was this translation helpful? Give feedback.
-
Thanks for your answers! @AyushExel, indeed, I would need to also eliminate the actual saving of all images to be compliant. @glenn-jocher, interesting shortcut. So adding a condition L113 if not --nomedia is what you suggest as a fix? |
Beta Was this translation helpful? Give feedback.
-
@glenn-jocher @ameicler I've made a PR that enables a |
Beta Was this translation helpful? Give feedback.
-
@ameicler good news 😃! Your original issue may now be fixed ✅ in PR #7534 by @AyushExel and myself. This PR adds a Usage example and expected output in runs/train/exp directory are below: python train.py --noplots To receive this update:
Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀! |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
Thanks for this extensive and powerful yolov5 implementation.
I was wondering if there was an easy way (through parameters or commenting some part of code) to activate wandb logging but without storing (or sending) any image?
Thanks for your help.
Beta Was this translation helpful? Give feedback.
All reactions