search

facebookresearch / co-tracker

CoTracker is a model for tracking any point (pixel) on a video.
https://co-tracker.github.io/
Other
2.52k stars 177 forks source link

Full video in memory #17

Closed bhack closed 11 months ago

bhack commented 11 months ago

Is there a way to avoid to load the full video in memory. Specially cause currently the full video is loaded in memory at full-res before you rescale it internally with video = F.interpolate(video, tuple(self.interp_shape), mode="bilinear")

nikitakaraevv commented 11 months ago

Hi @bhack, you can resize the video to the interpolation resolution (384x512) before feeding it to the model. If you wish to obtain trajectories in the original resolution, simply multiply them by the ratio between the original and resized resolutions.

bhack commented 11 months ago

If you wish to obtain trajectories in the original resolution, simply multiply them by the ratio between the original and resized resolutions.

This was already done by the current code in the repository. I was looking just for an ablation at higher resolution.