dataset about self-supervised-depth-completion HOT 3 OPEN

Hi. Hopefully the data directory structure is clear from the README file (copied and pasted here):

.
├── self-supervised-depth-completion
├── data
|   ├── kitti_depth
|   |   ├── train
|   |   ├── val_selection_cropped
|   └── kitti_rgb
|   |   ├── train
|   |   ├── val_selection_cropped
├── results

from self-supervised-depth-completion.

Hi!, i find your work really interesting. I want to evaluate your architecture with pre-trained weights only. what should be the structure of the data folder in that case.

The thing is kitti_rgb train is so big and i have to transfer all the files via SSH.

from self-supervised-depth-completion.

what should be the structure of the data folder in that case

The data folder structure is illustrated in the README. You can switch to any data loader, as long as the final loaded data format is the same

from self-supervised-depth-completion.