You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for your great project. I try to train monodepth2 with ARN module for tum dataset(most of sequences, every sequence for per 5 frame sampling, hw=640480, mono train mode with gt_depth), and I find the old monodepth2 could not handle this dataset well, cause every step the loss is 0, while monodepth2 with ARN could work a litter(loss could drop from 0.2 to 0.05 by ARN module loss funtion), where should I pay attention to when add ARN to monodepth2 as a seperate module in mono train mode?
The text was updated successfully, but these errors were encountered:
I didn't try it directly on the monodepth2 framework. I suggest that you use our PyTorch lightning re-implementation https://github.com/JiawangBian/sc_depth_pl, where we have added the features of monodepth2 (minimum loss, auto-mask) into our baseline.
Thank you for your great project. I try to train monodepth2 with ARN module for tum dataset(most of sequences, every sequence for per 5 frame sampling, hw=640480, mono train mode with gt_depth), and I find the old monodepth2 could not handle this dataset well, cause every step the loss is 0, while monodepth2 with ARN could work a litter(loss could drop from 0.2 to 0.05 by ARN module loss funtion), where should I pay attention to when add ARN to monodepth2 as a seperate module in mono train mode?
The text was updated successfully, but these errors were encountered: