We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
作者您好,我看到有人提出相似的问题,但是没有找到答案。
我采用batchsize 8 iter60000 初始0.01学习率的策略,但是最终只能在cityscapes val上到大约67%,68%的miou(STDC1-50)。 我使用的训练脚本就是github README.MD中的训练脚本。
请问我是不是哪里使用错误了么?为什么原封不动的使用您的代码,却无法达到(或者接近)您论文中的mIOU指标?至少相差6-7个百分点)
希望您能给点建议,非常感谢!
训练脚本如下:
export CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch \ --nproc_per_node=1 train.py \ --respath checkpoints/train_STDC1-Seg/ \ --backbone STDCNet813 \ --mode train \ --n_workers_train 12 \ --n_workers_val 1 \ --max_iter 60000 \ --use_boundary_8 True \ --pretrain_path checkpoints/STDCNet813M_73.91.tar
The text was updated successfully, but these errors were encountered:
你好,请问你现在复现到了吗,是不是初始学习率设置的问题
Sorry, something went wrong.
一样无法复现,STDC2最高精度如图
No branches or pull requests
作者您好,我看到有人提出相似的问题,但是没有找到答案。
我采用batchsize 8 iter60000 初始0.01学习率的策略,但是最终只能在cityscapes val上到大约67%,68%的miou(STDC1-50)。
我使用的训练脚本就是github README.MD中的训练脚本。
请问我是不是哪里使用错误了么?为什么原封不动的使用您的代码,却无法达到(或者接近)您论文中的mIOU指标?至少相差6-7个百分点)
希望您能给点建议,非常感谢!
训练脚本如下:
The text was updated successfully, but these errors were encountered: