Training time of Co-tracker

Question

Training time of Co-tracker

memoiry opened this issue a year ago · 3 comments

memoiry commented a year ago

Hi,

do we know how long it takes to finish 50,000 iterations with 32 V100 GPU?

Thanks!

Answer 1 · 2023-08-14T17:54:23.000Z

Hi @memoiry, for us, it takes around 40 hours with regular evaluations.

Answer 2 · 2023-08-23T02:06:41.000Z

Thanks! @nikitakaraevv , do you have any thoughts on how to do the windowed inference for realtime usage? I just thought a dumb “Window” approach where we windowed inference on every new frame, which might be time-consuming.

Answer 3 · 2023-09-01T15:10:56.000Z

Hi @memoiry, you could train a model with a sliding window of size 4. It is not much worse than the default window of size 8 (we have this experiment in the paper supplement). In this case, the lag will be only 1 frame (because the size of the overlap is 2 frames).
For true real-time inference, you could train the model with a sliding window of size 2. This would eliminate lag, but we haven't tested it yet. :)