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

多卡训练的精度和比单卡精度低的问题 #20

Open
xiguafeichong opened this issue Aug 22, 2021 · 2 comments
Open

多卡训练的精度和比单卡精度低的问题 #20

xiguafeichong opened this issue Aug 22, 2021 · 2 comments

Comments

@xiguafeichong
Copy link

跑market1501数据集,全部默认配置,bz=64,单卡map有88.4,4卡的精度只有85.5,请教下各位大佬,这到底是怎么回事,或者应该怎么调整

@Hellomodo
Copy link
Collaborator

我理解单卡变成4卡后,实际的batchsize已经和原来不一样了,可以试试调整学习率。

@Alexadlu
Copy link

请问为什么我设置多卡训练会出现如下错误, 而单卡训练是正常的
Traceback (most recent call last):
File "tools/main.py", line 110, in
main()
File "tools/main.py", line 70, in main
criterion = model.get_creterion(cfg, num_classes)
File "/home/yuanhui/anaconda3/envs/agw1/lib/python3.6/site-packages/torch/nn/modules/module.py", line 576, in getattr
type(self).name, name))
AttributeError: 'DataParallel' object has no attribute 'get_creterion'

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