data shape problem

[pcshih]

The original frame feature shape is [320,1024]

But the code https://github.com/weirme/Video_Summary_using_FCSN/blob/96b40851b7805afd1f1fc69f2beb5143d5727b4e/data_loader.py#L18
wants to reshape to [1024,320] directly.

Should it use transpose instead of reshape?

Thank you.

[weirme]

Thank you a lot, I think you are right and I have fixed this problem. But it's strange that F-score after modification seems to be almost same as before...

[pcshih]

Thank you a lot, I think you are right and I have fixed this problem. But it's strange that F-score after modification seems to be almost same as before...

Did you mean that the F-score is not same as the paper?

[weirme]

Thank you a lot, I think you are right and I have fixed this problem. But it's strange that F-score after modification seems to be almost same as before...

Did you mean that the F-score is not same as the paper?

F-score of the modified code and previous wrong code seems to be almost same.

[pcshih]

I implement myself by revising your code.
I got the performance quite well.
github

[weirme]

I implement myself by revising your code.
I got the performance quite well.
github

Yes, this code performs well on TVSum dataset.