Could anyone give some advice about how to do data augmentation on training which the paper said
"We perturb the training set by randomly rotating and translating the target
face in 2D image plane. To be specifc, the rotation is from -45 to 45 degree angles,
translation changes is random from 10 percent of input size, and scale is from
0.9 to 1.2. Like [18], we also augment our training data by scaling color channels
with scale range from 0.6 to 1.4. In order to handle images with occlusions, we
synthesize occlusions by adding noise texture into raw images, which is similar
to the work of [61,29]. With all above augmentation operations, our training
data covers all the difficult cases."
If someone is willing to share the training code, please send email to bantiauo@gmail.com.
Thanks!
Could anyone give some advice about how to do data augmentation on training which the paper said
"We perturb the training set by randomly rotating and translating the target face in 2D image plane. To be specifc, the rotation is from -45 to 45 degree angles, translation changes is random from 10 percent of input size, and scale is from 0.9 to 1.2. Like [18], we also augment our training data by scaling color channels with scale range from 0.6 to 1.4. In order to handle images with occlusions, we synthesize occlusions by adding noise texture into raw images, which is similar to the work of [61,29]. With all above augmentation operations, our training data covers all the difficult cases."
If someone is willing to share the training code, please send email to bantiauo@gmail.com. Thanks!