Skip to content
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

DDRNet相关问题 #27

Open
xiaoer666 opened this issue May 28, 2023 · 4 comments
Open

DDRNet相关问题 #27

xiaoer666 opened this issue May 28, 2023 · 4 comments

Comments

@xiaoer666
Copy link

你好,你这代码写的很好鲁棒性很强!但是我在本地单卡3060训练DDRNet23_slim,训练参数如下的情况下,跑出来结果只有70%

python -m torch.distributed.launch --nproc_per_node=1 \
                train.py --model DDRNet --out_stride 8 \
                --max_epochs 200 --val_epochs 20 --batch_size 6 --lr 0.01 --optim sgd --loss ProbOhemCrossEntropy2d \
                --base_size 768 --crop_size 768  --tile_hw_size 768,768 \
                --root 'data' --dataset cityscapes --gpus_id 0

这是什么原因呢,可以分享下复现DDRNet的参数吗,或者帮忙分析下是啥原因呀,感谢!

@zw4591423
Copy link

hey @xiaoer666 have u ever slove this issues? why i only get 66% mIou while using the base_size and crop size both 1024 other parampers keep same?

@xiaoer666
Copy link
Author

I didn't reproduce. Did you load the pre-trained model.I only get 70% mIou.

@zw4591423
Copy link

@xiaoer666 Not yet. Just learn from scratch.

@Deeachain
Copy link
Owner

你好,你这代码写的很好鲁棒性很强!但是我在本地单卡3060训练DDRNet23_slim,训练参数如下的情况下,跑出来结果只有70%

python -m torch.distributed.launch --nproc_per_node=1 \
                train.py --model DDRNet --out_stride 8 \
                --max_epochs 200 --val_epochs 20 --batch_size 6 --lr 0.01 --optim sgd --loss ProbOhemCrossEntropy2d \
                --base_size 768 --crop_size 768  --tile_hw_size 768,768 \
                --root 'data' --dataset cityscapes --gpus_id 0

这是什么原因呢,可以分享下复现DDRNet的参数吗,或者帮忙分析下是啥原因呀,感谢!

可以增大batch_size尝试,我的指标是基于四张卡实现的

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants