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

About the training iterations #13

Open
stark1092 opened this issue Aug 25, 2020 · 1 comment
Open

About the training iterations #13

stark1092 opened this issue Aug 25, 2020 · 1 comment

Comments

@stark1092
Copy link

Hi, thanks for your release of this code.
I have a problem about the training iteration on kitti_odometry data.
There are 20400 pairs of images as the training data, and batch size is 8, iteration is 200000.
So the training of the odometry data has 200000/(20400/8) = 78 epochs.
But in the paper, you just train flow/depth for 20 epochs.
If I want to reproduce the result, which iteration should I take?
Or my understanding of this parameter is wrong?
Waiting for your reply, thanks!

@thuzhaowang
Copy link
Collaborator

Hi @stark1092, please use the hyper-parameter settings in the code.

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