Total training time on THUMOS14

[ivyvideo]

Hi, I am running the code and find that it takes about two hours every 1000 iterations on Tesla M40, and I noticed that the default iteration is 60k totally...so it may cost so long time to finish training...
What is the reason for that? And what is your original training time?
Thanks!

[huijuan88]

If you resize the frames to be smaller, it would run faster. It also has a relationship with your machine. I am ~3 seconds per iteration. On Aug 28, 2018, at 05:45, ivyvideo <[email protected]<mailto:[email protected]>> wrote: Hi, I am running the code and find that it takes about two hours every 1000 iterations on , and I noticed that the default iteration is 60k totally...so it may cost so long time to finish training... What is the reason for that? And what is your origin training time? Thanks! — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub<#39>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AFOa_3Y3stiO76Vx_xuaGoIjpOlqOuMNks5uVRFWgaJpZM4WPRJX>.

[ivyvideo]

Is it related to the setting: cfg.TRAIN.VIDEO_BATCH = 1? Maybe I should set this parameter larger? Like 32 or 64?

[ivyvideo]

Sorry but I have another question... as shown below in the picture(part of minibatch.py), the parameter "fg_rois_per_video" is not used anymore after being assigned a value... so the network deals with 512 frames in only one video segment during forward process? And the batch_size is not used, either. Am I right?

[huijuan88]

Currently only one video in a batch. On Aug 29, 2018, at 04:05, ivyvideo <[email protected]<mailto:[email protected]>> wrote: Sorry but I have another question... as shown below in the picture(part of minibatch.py), the parameter "fg_rois_per_video" is not used anymore after being assigned a value... so the network deals with 512 frames in only one video segment during forward process? And the batch_size is not used, either. Am I right? [image]<https://user-images.githubusercontent.com/42105211/44774273-4592c400-aba5-11e8-8898-ea82b849af8a.png> — You are receiving this because you commented. Reply to this email directly, view it on GitHub<#39 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AFOa_7cM4q9c4h44iXnhRitJUZ4NkPUnks5uVksvgaJpZM4WPRJX>.

[ivyvideo]

Thank you so much for the kind reply.

[ivyvideo]

@huijuan88 I have one more question...have you tested setting the "video_batch" more than 1?

[huijuan88]

No. That part is not implemented. On Aug 30, 2018, at 18:30, ivyvideo <[email protected]<mailto:[email protected]>> wrote: @huijuan88<https://github.com/huijuan88> I have one more question...have you tested setting the "video_batch" more than 1? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub<#39 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AFOa_613oU-RQmzPC23Cf42c1zlVJgCMks5uWJHLgaJpZM4WPRJX>.

[ivyvideo]

OK, your help is greatly appreciated~~