-
Notifications
You must be signed in to change notification settings - Fork 0
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
作者你好,我有一个问题 #3
Comments
xxhPro
changed the title
作者你好,请问test_2d_forall_fast_txtver_forTrainSetUncertaintyOnly_Mean.py这个文件的第164行pred_uncertainty_unanotated_show = convertMap(pred_uncertainty_unanotated_show) # 4 is annotated, 0 is background的这行代码是不是可以去掉嘛,它总是说pred_uncertainty_unanotated_show之前未赋值
作者你好,我有一个问题
Dec 16, 2024
This line of code is just for visualization, and you can comment it out. Also, thank you for your question—I have already modified that line of code. |
ok,我已经注释掉了
…------------------ 原始邮件 ------------------
发件人: "HiLab-git/DMSPS" ***@***.***>;
发送时间: 2025年1月9日(星期四) 下午4:22
***@***.***>;
***@***.******@***.***>;
主题: Re: [HiLab-git/DMSPS] 作者你好,我有一个问题 (Issue #3)
请问test_2d_forall_fast_txtver_forTrainSetUncertaintyOnly_Mean.py这个文件的第164行pred_uncertainty_unanotated_show = convertMap(pred_uncertainty_unanotated_show) # 4 is annotated, 0 is background的这行代码是不是可以去掉嘛,它总是说pred_uncertainty_unanotated_show之前未赋值
This line of code is just for visualization, and you can comment it out. Also, thank you for your question—I have already modified that line of code.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
感谢你耐心的等待。期待你的成果。
***@***.***
…---- 回复的原邮件 ----
发件人
QinNan ***@***.***>
发送日期
2025年1月9日 16:31
收件人
***@***.***>
抄送人
Meng ***@***.***>
,
***@***.***>
主题
Re: [HiLab-git/DMSPS] 作者你好,我有一个问题 (Issue #3)
ok,我已经注释掉了
------------------ 原始邮件 ------------------
发件人: "HiLab-git/DMSPS" ***@***.***>;
发送时间: 2025年1月9日(星期四) 下午4:22
***@***.***>;
***@***.******@***.***>;
主题: Re: [HiLab-git/DMSPS] 作者你好,我有一个问题 (Issue #3)
请问test_2d_forall_fast_txtver_forTrainSetUncertaintyOnly_Mean.py这个文件的第164行pred_uncertainty_unanotated_show = convertMap(pred_uncertainty_unanotated_show) # 4 is annotated, 0 is background的这行代码是不是可以去掉嘛,它总是说pred_uncertainty_unanotated_show之前未赋值
This line of code is just for visualization, and you can comment it out. Also, thank you for your question—I have already modified that line of code.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you commented.Message ID: ***@***.***>
|
我看word论文这篇里面在使用nnunet模型分割3Dword数据集的时候把batch_size设置2是最佳的。你这边的代码说是因为gpu显存不够,所以batch_size设置为1。现在我这边的服务器是8块4090的,那么我是不是可以把batch_size设置为8,iterations设置为10000呢?还是说照着word论文里面的实验把batch_size设置为2,然后iterations还是跟着代码里面一样为60000呢?
Message ID: ***@***.***>
|
你好!
首先回答word论文里使用的设备和本论文是有差异的,所以设置不同。如果显存够的话,你可以任意设置batch_size,iterations的设置可以根据max epoch来。我的设置中max_epoch是600以保证训练比较充分。如果你batch_size比较大的话iteration就可以设置小一点。我觉得1w是可以的。【其实最主要的原则就是,只要你对比其他实验的时候所有实验的设置是一样的,确保公平就好了】
***@***.***
…---- 回复的原邮件 ----
发件人
QinNan ***@***.***>
发送日期
2025年1月14日 23:38
收件人
***@***.***>
抄送人
Meng ***@***.***>
,
***@***.***>
主题
Re: [HiLab-git/DMSPS] 作者你好,我有一个问题 (Issue #3)
我看word论文这篇里面在使用nnunet模型分割3Dword数据集的时候把batch_size设置2是最佳的。你这边的代码说是因为gpu显存不够,所以batch_size设置为1。现在我这边的服务器是8块4090的,那么我是不是可以把batch_size设置为8,iterations设置为10000呢?还是说照着word论文里面的实验把batch_size设置为2,然后iterations还是跟着代码里面一样为60000呢?
Message ID: ***@***.***>
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you commented.Message ID: ***@***.***>
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
请问test_2d_forall_fast_txtver_forTrainSetUncertaintyOnly_Mean.py这个文件的第164行pred_uncertainty_unanotated_show = convertMap(pred_uncertainty_unanotated_show) # 4 is annotated, 0 is background的这行代码是不是可以去掉嘛,它总是说pred_uncertainty_unanotated_show之前未赋值
The text was updated successfully, but these errors were encountered: