luohongcheng

How to process ground-truth depth when training?

4

Hi~ _the original frames of size 640 × 480 pixels are down-sampled to 1/2 resolution and center-cropped to 304 × 228 pixels_ When I do the same operation to ground-truth,...

Your tensorflow code may have bugs, it is very hard to train.

2

Hi~ I have trained your network use the code provided and hyper-parameter in the paper. But I find it is very very hard to train, even the training dataset gets...