search

smu-ivpl / FastInterCU-VVC

Official implementation of "Deep Neural Network-based Fast Inter CU Splitting Algorithm for Versatile Video Coding (VVC) Standard"
29 stars 11 forks source link

model #3

Open cxsunny opened 2 years ago

cxsunny commented 2 years ago

Can the model pt file in the file be used directly? Why can't I run it?

unacanal commented 2 years ago

Yes. What kind of error occured? Have you checked the version of TorchScript?

cxsunny commented 2 years ago

I have solved this problem. However, there are still some unclear points in the paper. Why should we add the predicted results of the model after checking the merge mode rdcost? What is the logic?

unacanal commented 2 years ago

The target of this work is to reduce complexity of INTER modes, so the residual image is acquired right after Merge mode as the best CU at that point.

cxsunny commented 2 years ago

How to get the prediction image of CTU? Can you share the code of making data set?

Thank you very much.