I'm very confused about pretrained network VGG-19 which seems to apply on classfication,how does it work in image inpainting?There are hundreds of excellent networks.Why we just choose this one?the way we use the pretrained model is that we use the pretrained model and put the incomplete picture as model input,croping it to 224,and as a result,getting a coarse result?
I would very appreciate if you could help me,thank you!
@leehomyc Hi,
I'm very confused about pretrained network VGG-19 which seems to apply on classfication,how does it work in image inpainting?There are hundreds of excellent networks.Why we just choose this one?the way we use the pretrained model is that we use the pretrained model and put the incomplete picture as model input,croping it to 224,and as a result,getting a coarse result?
I would very appreciate if you could help me,thank you!
Thanks,