search

ok1zjf / VASNet

PyTorch implementation of the ACCV 2018-AIU2018 paper Video Summarization with Attention
MIT License
180 stars 48 forks source link

Test my own video #6

Open 18pxrsun opened 4 years ago

18pxrsun commented 4 years ago 
   Hello,I meet some questions when i want to test my own video.
   I need to get the following parameters:
              machine_summary = generate_summary(probs, cps, num_frames, nfps, positions)
   So I need to run the cpd_auto.py:
             def cpd_auto(K, ncp, vmax, desc_rate=1, **kwargs):
  But I don't know the meaning of the input parameters such as K,ncp,vmax,Could you tell me the how you use it?
   And It only return two paragrames,cps and scores2.How can i get the rest paragram in generate_summary such as positions and nfps?
   Wish your reply,Thanks a lot!
ok1zjf commented 4 years ago

The datasets we used already include the change points, thus we didn't need to configure the KTS. Nevertheless, you may want to request the exact KTS parameters from the authors of the pre-processed datasets (also referenced in the paper) http://www.eecs.qmul.ac.uk/~kz303/vsumm-reinforce/datasets.tar.gz and https://www.dropbox.com/s/ynl4jsa2mxohs16/data.zip?dl=0 or discuss the authors of the KTS http://lear.inrialpes.fr/people/potapov/med_summaries or https://github.com/TatsuyaShirakawa/KTS

Best Jiri