Different sparse input when each sample input is loaded

[TruongKhang]

Hi,
I have read your implementation and I have a question about your implementation of sparse depth input generation in NYU dataset. You generated the sparse input when the ground truth depth is loaded by dense_to_sparse function. But this sparse input maybe not the same at the next epoch when the ground truth depth is loaded again.
Do I understand correctly? If I misunderstand something, please explain it for me!

Thanks,

[fangchangma]

Hey @TruongKhang. You were right - the exact sampling pattern changes from frame to frame, and from epoch to epoch. This randomization is by design, such that the network does not overfit a particular set of sampling patterns.

[TruongKhang]

@fangchangma , is it reasonable when compared with the baseline methods? The input now is different for all methods.

[fangchangma]

is it reasonable when compared with the baseline methods

Which baseline methods were you referring to?