dust3r icon indicating copy to clipboard operation
dust3r copied to clipboard
verified publisher icon naver

Fix MegaDepth train/val split

Open akretz opened this issue 5 months ago • 0 comments

The __init__() function of the MegaDepth data loader has a split parameter. However, it never gets passed to the super initializer and so self.split never gets set. This means self.split is always None for the MegaDepth dataset and training data = validation data.

https://github.com/naver/dust3r/blob/4c24a6ebf04809f2cfe59915e51779c8984aaa40/dust3r/datasets/megadepth.py#L16-L29

akretz avatar Jul 10 '25 13:07 akretz