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

Deeplab V3+ #12

Closed
dannyhung1128 opened this issue May 5, 2018 · 1 comment
Closed

Deeplab V3+ #12

dannyhung1128 opened this issue May 5, 2018 · 1 comment

Comments

@dannyhung1128
Copy link

Hi,
Can I simply change the model you used in train.py in to deeplab v3+?
I was wondering why you didn't do so, should it be quite straight forward?

Thanks!

@kazuto1011
Copy link
Owner

I would say you can run the code but it's not appropriate for training the v3+ model.
You need to change parameters to observe (line 30 -- 49 in train.py and optimizer setting) and other hyperparameters such as #batch and #output_stride, to train batch normalization parameters in the added modules on top of the dilated ResNet.
I've not implemented the v3+ training protocol yet.

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

2 participants