The problem of realizing the pre training model

[thefoxsayold]

Hello!
Follow your steps to install the environment and relevant data. The experimental equipment and environment meet the requirements. According to the pre training model, only three steps are performed to generate a 500K vido that cannot be opened mp4。 Prompt the following warning， It's where I didn't set it？

BoZhang

[letian-zhang]

I have same problem. Do you have any solution?

[ostjul]

This seems to be a compression error of imageio not allowing uneven height or width like the original resolution from the KITTI dataset. You could try to resize the images before saving the video in line 1485 of main.py

[liuxinhai]

I successfully use the PotPlayer to open the .mp4 video.

[HCL283]

I have also encountered the same problem. May I know how to solve it