taking long time to test compared to FGT

[smandava98]

Hi @hitachinsk! Firstly, great work and am very impressed. I liked the performance of ISVI as compared to FGT however I noticed that (for a video of only 60 frames), ISVI is taking over an hour on an A100 80 GB GPU whereas FGT takes just a few minutes.

The issue is mainly in the backward flow where it is interpolating and filling in the missed pixels. E.g:

for indFrame in range(nFrame):
        # Index of missing pixel whose backward flow neighbor is from frame indFrame
        SourceFmInd = np.where(flowNN[:, 2, 0] == indFrame)

        print("{0:8d} pixels are from source Frame {1:3d}"
                        .format(len(SourceFmInd[0]), indFrame))
        # The location of the missing pixel whose backward flow neighbor is
        # from frame indFrame flowNN[SourceFmInd, 0, 0], flowNN[SourceFmInd, 1, 0]

        if len(SourceFmInd[0]) != 0:

Can you help me resolve this please?

[smandava98]

I also notice that crop blending is taking a long time as well.

[hitachinsk]

Hello, as far as I know, ISVI should not take so much time during inference. Please check the CUDA compilation of the Forward_warp package.