too much time for "corest sampling"

[Classmate-Huang]

Thank you for your work!!

I found that the training time is very long, especially during the "corest subsampling" step.

When you are training, how long does it take for a category?

It's been almost an hour without any progress...

[haobo827]

Hi my chengdu's friends!
I got the same problem with you: wait 'calculating distances...' long time, when I use kCenterGreedy(SamplingMethodf).
Do you know why? and have solved it?
Much appreciate!

[haobo827]

Thank you for your work!!

I found that the training time is very long, especially during the "corest subsampling" step.

When you are training, how long does it take for a category?

It's been almost an hour without any progress...

Hi my chengdu's friends!
I got the same problem with you, like...

[ZwkAlex]

Hi my chengdu's friends! I got the same problem with you: wait 'calculating distances...' long time, when I use kCenterGreedy(SamplingMethodf). Do you know why? and have solved it? Much appreciate!

I guess maybe because it's calculating minimum distance using cpu, it's about one and half hour on my cpu, and
lower coreset_sampling_ratio will reduce computation time, but it also reduce performance.

[haobo827]

you are right. and it's hard to avoid