LemonGraZ
LemonGraZ
@hogepodge Are there any updates? This is quite a problem working efficiency for us.
Same problem here, upgrading to Chrome 128.0.6613.85 (Official Build) (64-bit) crashed it. Worked with previous versions. We're on Label Studio v1.8 however.
@ArgoHA Do you have any news regarding the aspect ratio topic? I am unsure myself what is best for training? It seems so wrong to use squishing however there is...
@lz1004 Hm okay, but one should keep it consistent i guess, right? So when training with squish also inference with squish? But swapping training transformation out in the yaml with...
Okay, so you @lz1004 recommend to stay with squishing for both training and inference?
Perfect, thank you!
This is very nice!
@XiphosF Nice, i did just ended up with exactly the same p6 yaml as you :D Thanks for sharing and making a PR that quickly!
@XiphosF short question to your P6 variant. Why are staying at 128 channels in layer 2 and wait until layer 3 to extend to 256ch? ```yaml # YOLO11-P6 backbone backbone:...
It's where the "