YufeiWang777 / LRRU

Official implementation of ``LRRU: Long-short Range Recurrent Updating Networks for Depth Completion'', ICCV 2023.
75 stars 2 forks source link

How to reproduce the performance on the NYU dataset ? #11

Open chenlongwhu opened 4 months ago

chenlongwhu commented 4 months ago

Thank you for your excellent work! I found that this repo is missing the training code on NYU DepthV2. I tried to use the data loader provided by NLSPN to reproduce your results, but there was a size error. I believe that some parameters of the network do not match the size of the NYU dataset. How can I solve this problem?

image