datasets about fcsn HOT 8 OPEN

Can't you open dataset?

if you can't open, access here for this model.
this link is same data.

from fcsn.

When training the tvsum dataset, the range of index in the data_loader.py file always exceeds the number of datasets, and there is a problem with the code.

from fcsn.

Yes, Maybe you should edit a code in data_loader.py

video=self.data_file['video_'+str(index.item())]
to
video=self.data_file['video_'+str(index)]

beacuse "index" is just variable stored int data-type.

from fcsn.

our test code does not get the accuracy rate and the recall rate.

from fcsn.

Will you improve the test code? Such as visualization, generating video, and getting accurate f-scores

from fcsn.

I would be able to do.. Maybe ^^.
I will try to visualize loss and acc graph, generate summarization and calculate f-scores.
But i want you to know, i'm not good at programming skills.
Thank you^^

from fcsn.

Do you have WeChat or email? Some questions want to ask you。

from fcsn.

my email is [email protected]

if i know answer for you questions. i can.

if is not, i will answer. but i will try to solve.

from fcsn.