Question about the depth prediction result

[yangengt123]

Hi tinghuiz,
I tried your code recently. It worked cool! But after completing all the steps you stated on the website, I found a problem here.

I believe I strictly followed your steps, and trained the model for 200K steps (the default value in your code). The evaluated depth accuracy I got was as follows:
abs_rel, sq_rel, rms, log_rms, d1_all, a1, a2, a3
0.2331, 3.7935, 7.4710, 0.3076, 0.0000, 0.7006, 0.8807, 0.9453

I also tried to disable the pose net and fit the ground truth pose to the model, and got the results shown below.
abs_rel, sq_rel, rms, log_rms, d1_all, a1, a2, a3
0.1889, 2.1794, 6.6112, 0.2708, 0.0000, 0.7413, 0.9053, 0.9597

It seems still worse than the result you post on the page. Is there any further fine-tuning should I make to reach the results rather than simply running the code directly?

Thanks!

[tinghuiz]

The final model I used was trained less than 200K steps (somewhere around ~160K I believe), as I noticed that the model started overfitting with longer training. As pointed out in another issue (#34), the weight decay is currently not applied correctly. Adding it could potentially alleviate the overfitting problem.