You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
about how the label file should be written as. From reading the paper, I understand that your Disentangling Conditional GAN perfoms color regression rather than categorical classification.
, I figure that labels is a pickle dump of a dictionary. Are the keys of this dictionary names of the images and values of this dictionary numpy arrays of RGB values?
The text was updated successfully, but these errors were encountered:
Yes, in the paper, we perform color regression. The dictionary structure is as you have described, the keys are the file name of an image, and the values are the average RGB color of the associated object in the image. I will create an updated branch soon with an example toy dataset, I hope it will be clearer for you as well.
Hi,
I couldn't figure out from the Readme.md and
disentangling_conditional_gans/dataset.py
Line 89 in 03d5101
about how the label file should be written as. From reading the paper, I understand that your Disentangling Conditional GAN perfoms color regression rather than categorical classification.
From
disentangling_conditional_gans/dataset_tool.py
Line 636 in 03d5101
The text was updated successfully, but these errors were encountered: