Deep-Alignment-Network-A-convolutional-neural-network-for-robust-face-alignment Normal face, mean and std are not used for testing?

Normal face, mean and std are not used for testing?

Open lcybuzz opened this issue 6 years ago • 0 comments

When mode is set to predict, mean_shape, imgs_mean and imgs_std are set to None. So I think inputs are not normalized and normal face is not used when building the network.

If I'm correct, why are these variables not used for predicting? Thanks for any idea!

Feb 15 '19 08:02 lcybuzz

Deep-Alignment-Network-A-convolutional-neural-network-for-robust-face-alignment Deep-Alignment-Network-A-convolutional-neural-network-for-robust-face-alignment copied to clipboard

Normal face, mean and std are not used for testing?

Deep-Alignment-Network-A-convolutional-neural-network-for-robust-face-alignment
Deep-Alignment-Network-A-convolutional-neural-network-for-robust-face-alignment copied to clipboard