about the label

[hk003]

you give an example of labels of the true ,part,negtive face image. true is 1,part 1,neg 0 why true and part have the same label.some other Programmers set part as -1,
is it practical to train models?

[foreverYoungGitHub]

I think yes. Since this label means that whether the face can be classified as a face, while the value of this label can be considered as the confidence of the face.

[yanzi6969]

能共享下 label_path = '../dataset/label.txt' landmark_path = '../dataset/landmark.txt' regression_box_path = '../dataset/regression_box.txt' crop_image_path = '../dataset/crop_image.txt' 这几个txt吗？实在没搞懂具体格式该怎样，谢谢

[Cbanyungong]

Sorry to bother you.Could I ask you a question?in the regression label,you have give an example 'face regression: [0.1,0.1,0.1,0.1]',the numbers denote the position of the face in an image.I wonder if the a face occupies the whole image ,can the position be written like this:[0,0,1,1].If all of my images were labeled like this,How will this affect my experiments?

[yanzi6969]

@foreverYoungGitHub face regression: [0.1,0.1,0.1,0.1]. left_x,left_y,width,height or left_x, left_y, ritht_x, ritht_y?