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
Hello,
Thank you so much for providing the code for this paper :)
I am trying to generate an annotated face dataset, but I am having some trouble with the train_deeplab.py.
In ln[95] there is all_pickle = glob.glob(data_path + '/*.pickle'), which loads the 16 manually annotated data if I understood the docs correctly. However, I can't seem to find these .pickle files.
I guess one can load the training/test data provided in dataset_release, but it would still be missing the uncertainty_score.
The text was updated successfully, but these errors were encountered:
Thank you so much for your reply :)
The annotations of face images are lacking color/labels, it is similar to what #36 reported. Does this have anything to do with the color palette chosen?
Hello,
Thank you so much for providing the code for this paper :)
I am trying to generate an annotated face dataset, but I am having some trouble with the
train_deeplab.py
.In ln[95] there is
all_pickle = glob.glob(data_path + '/*.pickle')
, which loads the 16 manually annotated data if I understood the docs correctly. However, I can't seem to find these.pickle
files.I guess one can load the training/test data provided in
dataset_release
, but it would still be missing theuncertainty_score
.The text was updated successfully, but these errors were encountered: