The results are not as yours about monodepth HOT 8 CLOSED

Thank you for your answer.
The name of results in the website misleading me.
So, I need train a cityscapes model.

from monodepth.

Hi,
Could you please me bit more specific?
What results and how are they different?

from monodepth.

The result in matrix just range from 0.14x to 0.15x. You can find that it is wrong.
In your results: http://visual.cs.ucl.ac.uk/pubs/monoDepth/results/.
The range is from near 0 to about 0.1.
Why?
There are some things diferent?
I just test the cityscapes models.

from monodepth.

What data do you use for testing?

from monodepth.

The cityscapes
All testing data in berlin:
berlin/berlin_000000_000019_leftImg8bit.png berlin/berlin_000000_000019_rightImg8bit.png
.....

from monodepth.

The output disparities we provide are only on the KITTI dataset (kitti or eigen split) you are testing on cityscapes which is a different dataset.
We did not upload the output disparities for the cityscapes dataset.

from monodepth.

@mrharicot
Hello, I also download the model_cityscapes model and tested on the cityscapes test dataset and got the disparities_pp.npy, then i used the evaluation code to evaluation the results, but i got the results are not as yours in the paper:

abs_rel, sq_rel, rms, log_rms, d1_all, a1, a2, a3
0.4235, 3159.2678, 18126.822, 1.910, 67.391, 0.338, 0.716, 0.762

I did change the focal to 2262 and the baseline to 0.22.
`
width_to_focal[2048] = 2262
def convert_disps_to_depths_cityscapes(gt_disparities, pred_disparities):
gt_depths = []
pred_depths = []
pred_disparities_resized = []

for i in range(len(gt_disparities)):
    gt_disp = gt_disparities[i]
    height, width = gt_disp.shape

    pred_disp = pred_disparities[i]
    pred_disp = width * cv2.resize(pred_disp, (width, height), interpolation=cv2.INTER_LINEAR)

    pred_disparities_resized.append(pred_disp) 

    mask = gt_disp > 0

    gt_depth = width_to_focal[width] * 0.22 / (gt_disp + (1.0 - mask))
    pred_depth = width_to_focal[width] * 0.22 / pred_disp

    gt_depths.append(gt_depth)
    pred_depths.append(pred_depth)
return gt_depths, pred_depths, pred_disparities_resized`

I do not know what went wrong,??

from monodepth.

Hi,
We did not test our model on the cityscapes dataset as they do not have reliable depth data.
What results are you comparing it with?

from monodepth.