img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) How do we get these numbers,Why aren't they the same with ImageNet's norm_cfg? ImageNet's norm_cfg :mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225] ...
I was trying to train my detector on the PASCAL VOC dataset. I noticed that the image normalization parameter - std values in ssd512_voc.py and ssd300_voc.py img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True) are different from those in faster_rcn...