Open pat-hanbury opened 5 years ago
Hi, Thanks for your interest! I checked your GIF files, it seems that the size of the input image is 256x256, however, the provided pre-trained models were trained by using images of size 128x128. So could please run the inference again with images of a smaller size?
Also, we have also fixed the error you reported.
Hello,
I am trying to recreate the results on UCF-101 using the provided pretrained models for
PlayingViolin
andIceDancing
. I am using thetest_refine.py
script for testing, but I am getting odd results:The only thing in the code I changed to make the code run is: https://github.com/junting/seg2vid/blob/8240c8cae9ed3c12fdf0aa9c0432e4336dddbcd0/src/test_refine.py#L123
I had to change this line from
z_m = Vb(z_noise.repeat(frame1.size()[0] * 8, 1))
toz_m = Vb(z_noise.repeat(frame1.size()[0] * 2 * 8, 1))
Without this change, I received an error complaining about the incorrect size of
z_m
.Please advise on more details about UCF-101 inferences in order to reproduce your result. Thank you in advance!