search

karanvivekbhargava / obamanet

ObamaNet : Photo-realistic lip-sync from audio (Unofficial port)
MIT License
237 stars 71 forks source link

Framerate to extract images from video? #13

Open wanshun123 opened 5 years ago

wanshun123 commented 5 years ago

In the readme the command for converting videos to images is as follows:

ffmpeg -i 00001.mp4 -r 1/5 -vf scale=-1:720 images/00001-$filename%05d.bmp

This will only extract an image every 5 seconds (per -r 1/5) - is this how it should be done and if so, why? Is this arbitrary? I see in processing.py it indicates only 1467 images from 20 videos were used to generate the image_kp_raw files which indicates this is how it was done.

karanvivekbhargava commented 5 years ago

@wanshun123 That 1467 is the number of clips. The -r is not used in the processing.py at all. So I maintain the default framerates.