FastSAM icon indicating copy to clipboard operation
FastSAM copied to clipboard

Published 20 hours ago • verified publisher icon CASIA-IVA-Lab

Fine Tuning Code

Open Shivansh-Srivastava-techolution opened this issue 1 year ago • 11 comments

Hey, Huge thanks for such a great repo that you have made, just wanted to know if it can be fine tuned for specific purposes, it would be great if you could provide code to fine tune the model on COCO dataset.

Shivansh-Srivastava-techolution avatar Jun 23 '23 08:06 Shivansh-Srivastava-techolution

Looking forward to the training code.

unriddler avatar Jun 26 '23 02:06 unriddler

@zxDeepDiver Looking forward to the training code+1

EveningLin avatar Jun 26 '23 07:06 EveningLin

Looking forward to the training code+2

Xelawk avatar Jun 28 '23 03:06 Xelawk

Looking forward to the training code+3

githublqs avatar Jun 28 '23 07:06 githublqs

Looking forward to the training code+4

Zr2223 avatar Jun 28 '23 07:06 Zr2223

Looking forward to the training code+5

beyoursel avatar Jun 28 '23 08:06 beyoursel

Looking forward to the training code+6

mertikinci avatar Jun 28 '23 15:06 mertikinci

Looking forward to the training code+7

songbingze avatar Jun 29 '23 05:06 songbingze

Looking forward to the training code+8

j0987834204 avatar Jun 29 '23 08:06 j0987834204

Thanks very much for all of you for your attention! Training and fine-tuning codes will be put together and released soon!

Hey, Huge thanks for such a great repo that you have made, just wanted to know if it can be fine tuned for specific purposes, it would be great if you could provide code to fine tune the model on COCO dataset.

an-yongqi avatar Jun 29 '23 09:06 an-yongqi

@zxDeepDiver Looking forward to the training code+1

Thanks for your attention. The training scripts will be released for the better application in downstream scenarios.

zxDeepDiver avatar Jun 29 '23 09:06 zxDeepDiver

Thanks very much for all of you for your attention! Training and fine-tuning codes will be put together and released soon!

Hey, Huge thanks for such a great repo that you have made, just wanted to know if it can be fine tuned for specific purposes, it would be great if you could provide code to fine tune the model on COCO dataset.

Could you kindly provide an expected date when you guys will release it? It will be greatly appreciated!!

Sijie-L avatar Jul 10 '23 02:07 Sijie-L

The code is currently being organized to optimize its utility for downstream task fine-tuning scenarios. If you wish to promptly obtain the code for training or fine-tuning purposes, kindly reach out to us via email and specify your intended use case. We welcome your usage across various scenarios. For emailing, we recommend contacting us at [email protected].

an-yongqi avatar Jul 10 '23 02:07 an-yongqi

Hi @an-yongqi I have mailed regarding the finetuning code. Could you please check and revert bask?

AT38875 avatar Aug 09 '23 04:08 AT38875

Training code released: https://github.com/CASIA-IVA-Lab/FastSAM/blob/main/sa_hub/TRAIN.md

zxDeepDiver avatar Sep 11 '23 08:09 zxDeepDiver