Open isdj opened 1 year ago
Thank you. I have tried implementing MuP in 2 vision cases - hugging face ViT with an image classification head and segmenter.
While the results seem to have worked fine with the hugging face model I can't seem to reproduce the results with segmenter.
Please see this repository for the exact code I ran:
Hugging face model results are visible here Segmenter results are visible here here Segmenter tests were run using this script
Do you by any chance have some insight to why my results differ so drastically from yours on the segmentation model? Have I implemented MuP the wrong way?
Thank you
Did you run coord check?
Is there a reason the segmenter results are so noisy? Are you averaging your losses over training time and/or over seeds?
I'm not familiar with segmenter models, but maybe I can help if you point out how the segmenter model is different from a more typical image classifier and where you used muP.
Attached are the results of the coordcheck, it seems like the standard parameterization also get's reasonably "neat" results.
Hi,
I'm not aware of any such tests, but there is no reason muP wouldn't work on segmentation models.
On Sun, Nov 6, 2022, 12:21 PM isdj @.***> wrote: