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

train epoch #27

Open
Zhang-jiemmd opened this issue Jan 6, 2021 · 4 comments
Open

train epoch #27

Zhang-jiemmd opened this issue Jan 6, 2021 · 4 comments

Comments

@Zhang-jiemmd
Copy link

I want to know how many epochs you trained on the kitti dataset
I have trained 15 epochs,and best val miou is 47.082

@edwardzhou130
Copy link
Owner

edwardzhou130 commented Jan 6, 2021

As mentioned in #15, training with dropblock needs around 20 epochs to reach the highest mIoU.

@edwardzhou130
Copy link
Owner

But 47.082 at the 15th epoch is much lower than what I got. Are you using the default training settings in the code?

@Zhang-jiemmd
Copy link
Author

I set grid_size=[320, 320, 16], model='traditional'. Other parameters are the same as the default values.
Does the difference in such parameters have any effect?

@edwardzhou130
Copy link
Owner

Smaller grid_size generally has a lower mIoU, but it won't affect too much.

traditional model trains the same network in cartesian coordinates rather than in polar coordinates. Our experiment shows that its mIoU performance is lower than PolarNet.

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