mrharicot / monodepth

Unsupervised single image depth prediction with CNNs

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Test results not good after training on custom data

poornimajd opened this issue · comments

Hi, I have trained my model on Indian Driving dataset . But I get this as the output
0000000_disp
0000000
My data is similar to that of Kitti except that it is more challenging because it is on Indian roads , a unconstrained environment.
I have around 8k left camera images and 8k right camera images which are in a sequence. Can you please help me out with this?

I have also attached a few examples from my training data
0000008
0000133

Hi, are your images rectified?

No they are not rectified. I just gave the left and right camera images.In my opinion rectifying images was not mentioned in the repo.

Images should be rectified.

After rectifying I will get one image as a result,then should I give this as the only input for both left and right side images?

You will get two images after rectification.

Okay I will try out this once.Thanks !