New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

How to fine tune SegFormer on a custom dataset #3794

Open

MariaMel98 opened this issue Oct 15, 2024 · 0 comments

MariaMel98 commented Oct 15, 2024

Hello. I'm trying to fine tune a segformer model on my custom dataset. I have the images and masks as they should be for segformer in my dataset folder.
I follow this tutoria lhttps://github.com/open-mmlab/mmsegmentation/blob/v1.2.2/demo/MMSegmentation_Tutorial.ipynb which is for a pspnet model. So far i have:

from mmengine import Config
config_file = 'configs/segformer/segformer_mit-b0_8xb1-160k_cityscapes-1024x1024.py'
cfg = Config.fromfile(config_file)

I'm working on a single GPU. What attributes should i change to cfg in order to be able to do the training? Is there a tutorial for this?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment