tobyperrett

Could you please send me the link for the split as well as I am also having problems getting the whole dataset? Thanks.

Hi. Will some examples be provided? Thanks.

It looks like the ALPRO model does not have a predict_answers method. Would this would be needed to be implemented in the ALPRO class to do video QA as in...

I think I just did 8 frames per instance to save space. On Fri, 2 Dec 2022 at 09:30, Liu-arch ***@***.***> wrote: > Hello, I would like to ask how...

Uniformly sample 8 frames per instance, so it’s not a fixed frame rate. Different instances are different lengths, but the method only takes in a fixed number of frames. You...

Using the first 8 frames will obviously not work as most of the action will be missing. The functionality you want is in the shrink dataset script. It uniformly samples...

Use my few-shot repo instead of the trx one. It’s easier to use and has additional baselines etc. On Sun, 4 Dec 2022 at 16:41, Liu-arch ***@***.***> wrote: > Sorry,...

That repo has scripts for extracting data and for shrinking it down to 8 frames. On Sun, 4 Dec 2022 at 17:19, Liu-arch ***@***.***> wrote: > I just looked at...

It's been a while since I've used this, but I seem to remember that OTAM works best with tasks_per_batch=1 (they don't mention gradient accumulation in their paper). Others who've used...

In fact, that's what the setting is in scripts/examples.md. So just try running that command.