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 downloaded your code for the paper 'Two-Stream Convolutional Networks for Action Recognition in Videos', and run it directly. I tried many times but I can only get a result of 91.5%.
Should I change somewhere in your code to get the 92.5% in your paper?
The text was updated successfully, but these errors were encountered:
MubarkLa
changed the title
May I get the 92.5% accuracy by directly run your code?
Can I get the 92.5% accuracy by directly run your code?
Oct 31, 2016
Hi,
In the paper a different testing strategy is employed. "For testing we average
20 temporal predictions from each network by densely sampling the input-frame-stacks and their horizontal flips". Consider changing the opts.train.numValFrames variable.
Hello.
I downloaded your code for the paper 'Two-Stream Convolutional Networks for Action Recognition in Videos', and run it directly. I tried many times but I can only get a result of 91.5%.
Should I change somewhere in your code to get the 92.5% in your paper?
The text was updated successfully, but these errors were encountered: