Closed qiyan98 closed 2 years ago
As indicated in the F.interpolate
document, the default interpolation mode is nearest
. Do you think this could help to justify the regression label re-scaling?
mode (str) – algorithm used for upsampling: 'nearest' | 'linear' | 'bilinear' | 'bicubic' | 'trilinear' | 'area'. Default: 'nearest'
Thanks.
Hi,
yes, the nearest interpolation is important to not mix zeros (ie invalid labels) and non-zero entries. Results might differ for your specific project, but we have seen no problem with label re-scaling like this. Note, that depending on how you train (RGB mode, or end-to-end training) these labels are only used as a coarse target or an initialisation. The training will refine these labels in most circumstances. The only case where this not happens would we pre-training in RGB-D mode and then omitting end-to-end training.
Best, Eric
Hi,
Thanks for the wonderful open-sourced project (again)!
I have a question on the potentially harmful effects of label re-scaling. The re-scaling of the image is generally fine. But re-scaling for 3D labels may change the
0
value for invalid scene coordinate masks. https://github.com/vislearn/dsacstar/blob/3ffbcb1d4d7b0cae68902560b5a2296d8c1b77e6/dataset.py#L187-L199In the loss function, the mask is used as follows: https://github.com/vislearn/dsacstar/blob/3ffbcb1d4d7b0cae68902560b5a2296d8c1b77e6/train_init.py#L191-L192
We are concerned about this in our project as the training labels might become accurate after augmentation. I wondered if you have some insights on this issue.
Many thanks!