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
Why are we applying ImageNet normalization (mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) to images in MultiImageObsEncoder that have already been normalized to the range [-1, 1] in normalize_util.py with the function get_image_range_normalizer() ? Is this double normalization intentional?
The text was updated successfully, but these errors were encountered:
Why are we applying ImageNet normalization (mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) to images in MultiImageObsEncoder that have already been normalized to the range [-1, 1] in normalize_util.py with the function get_image_range_normalizer() ? Is this double normalization intentional?
The text was updated successfully, but these errors were encountered: