You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello!I am new to here . I want to know how to reproduce this excellent work.
First of all, I only downloaded UCF101 from TH14 official website. And I extracted the frame and optical flow to / home / win / pcharmprojects / datasets / thumbos14 / frame. But when I tried Python gen_ proposal_ list.py Thumbos14 / home / win / pycharmprojects / datasets / thumbos14 / frame, it appears keyerror: 'video'_ validation_ 0000354'
I guess it's because my data structure is not right? Maybe I need to download something else?Ask for help! Thank you very much!
The text was updated successfully, but these errors were encountered:
The experiments need the THUMOS14 dataset. It is different from the UCF101 dataset. UCF101 contains trimmed videos while THUMOS14 contains long untrimmed videos used for the temporal action detection task. Please obtain the download link from the official website.
@yjxiong
Hi ! I am so glad to see your reply! Because I see that the training set on TH14's official website is 20 types in ucf101, I downloaded UCF to train first. So should I train and test with Val and test data sets?
Hello!I am new to here . I want to know how to reproduce this excellent work.
First of all, I only downloaded UCF101 from TH14 official website. And I extracted the frame and optical flow to / home / win / pcharmprojects / datasets / thumbos14 / frame. But when I tried Python gen_ proposal_ list.py Thumbos14 / home / win / pycharmprojects / datasets / thumbos14 / frame, it appears keyerror: 'video'_ validation_ 0000354'
I guess it's because my data structure is not right? Maybe I need to download something else?Ask for help! Thank you very much!
The text was updated successfully, but these errors were encountered: