sylvainma / summarizer Goto Github PK

Your code is as beautiful as a poem!
Would you like to repeat the methods in other papers?

Hi there,
I wonder how can I generate the LOL dataset using my own feature extractor ?

Now I want to use the trained network to generate summary on custom videos, but I don't know the exact feature extractor (network) so the extracted feature vectors on TVSum is different from that from downloaded .h5 files. This could lead to a performance drop because of the input data distribution mismatch.

I have tried the GoogleNet pool5 from Torchvision pretrained model zoo, but look like the values are different totally.

Thanks for any advices.

The Readme doesn't describe how to use the project. Can anyone help?

Hi, I'm making video summaries on another dataset. Can you explan how to make KTS result on your file summarizer_dataset_*.h5.
I know the input of KTS. But I am wondering about 2 parameters on fuction cpd_auto: number of feature frames used and ncp - maximum ncp. How to determine ncp and number of features used.

I really appreciate your effort in creating this repository.
Can you please specify the usage of draw_score and draw_gtscore functions. Where these functions are called.