What if the new model using in 3D medical image segmentation?

gorkemcanates / Dual-Cross-Attention

Official Pytorch implementation of Dual Cross-Attention for Medical Image Segmentation

MIT License

102 stars 12 forks source link

Closed yjsb closed 1 year ago

yjsb commented 1 year ago

I want to use it on my 3D segmentation dataset.

gorkemcanates commented 1 year ago

You need to change 2d kernel sizes to 3d.

NetfriendT commented 2 months ago

You need to change 2d kernel sizes to 3d.

Do you just need to modify something like nn.ConvTranspose2d? Do those parts of attention need to be modified

NetfriendT commented 2 months ago

@yjsb Have you successfully applied DAC module to 3d? May I ask you about your modification method? Thank you so much