train_diffusion_2d.py

[luhaihenchang]

Hi, thanks for the code. I would like to ask, do train_diffusion_2d.py and train_diffusion.py in your code handle 2d slice data and 3d data respectively?
Is there a big difference in accuracy between running train_diffusion_2d.py and train_diffusion.py?

[McGregorWwww]

Thanks for your attention.

Yes, the two training scripts are independent. Actually, the 2D pipeline was included as a supplement to enhance the codebase's versatility for 2D tasks, we did not make a thorough comparison between 2d and 3d.
For the datasets mentioned in the paper, using 3D pipeline is better generally.

Hope this helps.