search

gangweiX / IGEV

[CVPR 2023] Iterative Geometry Encoding Volume for Stereo Matching and Multi-View Stereo
MIT License
541 stars 66 forks source link

n_downsample can't be changed #22

Open gutcBrEl opened 1 year ago

gutcBrEl commented 1 year ago

To reduce the size of the model, I want to retrain the network with lower resolution of the disparity field. I've already done this with the RAFT-Stereo network. However, when changing the corresponding parameter n_downsample from 2 to 3, the update_block throws a size mismatch error in this line.

It seems the cnet changes the resolution correctly, while the feature network keeps the original resolutions.

Can you supply a bugfix for this or describe, how you would change the network to allow different downsampling values?

Many thanks in advance!

gangweiX commented 1 year ago

Hello, in my network, I did not design a lower resolution, such as the case where n_downsample is 3, so you may need to manually adjust it.