ControlNet / LAV-DF

[CVIU] Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization
https://www.sciencedirect.com/science/article/pii/S1077314223001984
Other
67 stars 8 forks source link

Question about boundary sample map weight #17

Open yueyue1009 opened 5 months ago

yueyue1009 commented 5 months ago

Hi, thanks for the great work, I have a question about the function get_pem_smp_weight() of model.boundary_module.py.

At line 77 you assigned xmax = (j + 1), and at line 79 length = xmax - xmin. Based on your paper and the comment written in the file, I thought that xmax should be (i + j + 1) and length = (j + 1).

Consider a case that i = 10, and j = 0, in this case, xmax = 1, length = -9. it is quite confusing to me that how length < 0 mean.

Thanks for reading, please correct me if I am wrong.