activitynet_iter_30000_3fps.caffemodel

[jetyingjia]

Thanks a lot for sharing the code.
I am confused about this model?(activitynet_iter_30000_3fps.caffemodel)
a. It is a classification model or detection model?
b. how to get this model?
Thank you in advance!

[huijuan88]

It’s classification model for initialization, pretrained on ActivityNet ground truth segments. On Dec 19, 2017, at 20:26, jetyingjia <notifications@github.com<mailto:notifications@github.com>> wrote: Thanks a lot for sharing the code. I am confused about this model?(activitynet_iter_30000_3fps.caffemodel) a. It is a classification model or detection model? b. how to get this model? Thank you in advance! — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub<#5>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AFOa_wLWowkAqUfWk2n8NehXqlGho5fSks5tB6tYgaJpZM4RG4xC>.

[dsuthar-nvidia]

@jetyingjia Your question b still remains unanswered I guess.

[sunnyxiaohu]

Hi, huijuan
Have you evaluated the performance of thumos14 when using "activitynet_iter_30000_3fps.caffemodel" for pretraining ? It seems that it would be more helpful if using "activitynet_iter_30000_3fps.caffemodel" to initialize instead of "Sports-1M" .

[dsuthar-nvidia]

@jetyingjia The model is available at https://drive.google.com/file/d/131Cpuq1FndydeHzu38TY0baiS-uyN71w/view