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.

Sign up for GitHub

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

Jump to bottom

What is the function of "chunk_size"? #15

Open

Harry-Zhi opened this issue Dec 5, 2016 · 0 comments

Harry-Zhi commented Dec 5, 2016

Hi Dimatura,
Your paper and work are really inspiring.

I want to use Keras to repeat your work through the given codes.

I notice that in your codes you have augmented(jitter) and load the 3D voxel data in a size of "chunk_size * batch_size".

How about just take a mini batch of data (e.g.，we take a batch size of 32 in your code) every time before we jitter or load the data.

What's the purpose of processing the data regarding "chunk_size * batch_size" as a whole instead of just a mini batch of data without chunk_size？

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment