Scene-Text-Removal icon indicating copy to clipboard operation
Scene-Text-Removal copied to clipboard

Published 20 hours ago • verified publisher icon HCIILAB

Does L_total = 0.5 * L_perceptual + 50.0 * L_style + 25.0 * L_tv only apply to optimize VGG?

Open lovecambi opened this issue 5 years ago • 2 comments

https://github.com/HCIILAB/Scene-Text-Removal/blob/master/network.py#L78 https://github.com/HCIILAB/Scene-Text-Removal/blob/master/train.py#L167 The trainerV seems to only optimize parameters of VGG. So why this loss is needed?

https://github.com/HCIILAB/Scene-Text-Removal/blob/master/train.py#L157 This line I_comp = where(mask, real, fake) contradicts to the description in the paper where I_comp = where(mask, fake, real).

lovecambi avatar Feb 05 '20 08:02 lovecambi

@lovecambi，The trainerV,trainerD, and trainerG are trained alternately to optimize the results. for I_comp = where(mask, real, fake)， 1 and 0 of the mask represent non-text and text areas, respectively.

zhangshuaitao avatar Feb 13 '20 06:02 zhangshuaitao

@lovecambi，The trainerV,trainerD, and trainerG are trained alternately to optimize the results. for I_comp = where(mask, real, fake)， 1 and 0 of the mask represent non-text and text areas, respectively.

So for this line https://github.com/HCIILAB/Scene-Text-Removal/blob/master/train.py#L119 the mask here also uses 1 to represent non-text region?

lovecambi avatar Feb 13 '20 07:02 lovecambi