facebookresearch / consistent_depth

We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.
MIT License
1.62k stars 235 forks source link

Cannot find an image when running demo #15

Open KyoukaMinaduki opened 4 years ago

KyoukaMinaduki commented 4 years ago

Hello. I followed your instructions to run the demo. However, when I was running the command

"python main.py --video_file data/videos/ayush.mp4 --path results/ayush --camera_params "1671.770118, 540, 960" --camera_model "SIMPLE_PINHOLE" --make_video",

a FIleNotFoundError occurs:

FileNotFoundError: [Errno 2] No such file or directory: '/tmp/tmprh9hg3hs.png'

I wonder where can I obtained these images? Or whether I ignore something?

KyoukaMinaduki commented 4 years ago

Emmmm I suddenly found that I didnt download the ffmpeg. I wonder whether it is the reason?

BaiFree commented 4 years ago

I also encountered this problem, installing ffmpeg can solve it.

YUYING96 commented 3 years ago

I also met this problem, and even if I installed ffmpeg, this problem still existed, have you solved it now?

yudianzheng commented 1 year ago

Installing ffmpeg doesn't help me, unfortunately

lyx323 commented 1 year ago

you should install python ffmpeg in your conda enviroment, python ffmpeg, not ffmpeg in your PC fllowing this: conda install -c conda-forge ffmpeg-python