Window size for generating roi

[ivyvideo]

Thanks for your great contribution!
And I have one question about the window size for generating roi in generate_roidb_512.py

As shown above, you create a sliding window whose size is 512 to collect the data used for training, what confusing me is whether this parameter a empirical parameter? Or it is used after analysis on the thumos dataset?

[huijuan88]

Usually, it should roughly cover the longest activity duration in that fps. On Aug 27, 2018, at 03:26, ivyvideo <notifications@github.com<mailto:notifications@github.com>> wrote: Thanks for your great contribution! And I have one question about the window size for generating roi in generate_roidb_512.py [image]<https://user-images.githubusercontent.com/42105211/44646290-1ba69980-aa0d-11e8-9d6c-2a0d6047b974.png> As shown above, you create a sliding window whose size is 512 to collect the data used for training, what confusing me is whether this parameter a empirical parameter? Or it is used after statistics? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub<#38>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AFOa_9n-t8qq-qQv0i4MWy2AdCJ5f6LYks5uU58ugaJpZM4WNTwS>.

[ivyvideo]

@huijuan88 Thanks for reply! Got it.
And it has nothing to do with the output of Conv5b which has 512 channels, right?

[huijuan88]

No relationship with it. On Aug 28, 2018, at 04:10, ivyvideo <notifications@github.com<mailto:notifications@github.com>> wrote: @huijuan88<https://github.com/huijuan88> Thanks for reply! Got it. And it has nothing to do with the output of Conv5b which has 512 channels, right? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub<#38 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AFOa_9tY5tT4PZQBNETsFXmc5CdvGKp8ks5uVPr1gaJpZM4WNTwS>.

[ivyvideo]

ok, thank you so much!