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

[Model] timm backbone (encoder) #49

Open

Dongwoo-Im opened this issue May 5, 2022 · 2 comments

Labels

Contributor

Dongwoo-Im commented May 5, 2022 •

edited

Loading

추천 List

tu-tf_efficientnetv2_l_in21k : 1epoch 5분, 성능 good
https://wandb.ai/mg_generation/semantic_segmentation_dongwoo/runs/2rdchgkh?workspace=user-idw960510

비추 List

tu-resnetv2_101x3_bitm_in21k : 1epoch 13분, confusion_matix 보면 굉장히 헷갈려함
https://wandb.ai/mg_generation/semantic_segmentation_dongwoo/runs/22d7bytp?workspace=user-idw960510
tu-mobilenetv3_large_100_miil_in21k : epoch 1분30초, 속도는 빠르지만 성능은 낮은 편
https://wandb.ai/mg_generation/semantic_segmentation_dongwoo/runs/s5zlln3l?workspace=user-idw960510

Error List

Dongwoo-Im added the 📝Discussion label

Contributor

baekkr95 commented May 6, 2022

동우님 혹시 디코더 네트워크는 어떤거 사용하셨나요?

Contributor Author

Dongwoo-Im commented May 6, 2022

저는 FPN 사용중입니다!

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