-
Notifications
You must be signed in to change notification settings - Fork 176
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.
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
training setting for single-task (i.e., semantic segmentation in ade20k) in painter #45
Comments
ps: we use the mae_pretrain_vit_base.pth instead of large, is the base model need different hyper-params? |
I also trained Painter for single-task of semantic segmentation in ADE20K.
Hi @yixuan730, could you please report the value you got? Thanks! Hi @WXinlong, I was wondering if I missed something or the model was sensitive to batch size. Thank you so much! |
@essunny310 similar situation. |
train adek20 没有效果,请问解决了吗,谢谢 |
I got the same problem, do u have new results? |
Hi, what are the specific training settings for single-task of semantic segmentation in ade20k?
Now, our settings are: batch size=8 (per gpu), accumulate iterations=16, nodes=2, base lr=1e-3 (also tried actual lr=1e-3 which not worked), epoch=300, warmup epoch=20, layer decay=0.8.
However, this hyper-params setting is not worked. Is there something we're missing?
Thank you very much!
The text was updated successfully, but these errors were encountered: