search

penincillin / DREAM

This is the public repository for our accepted CVPR 2018 paper "Pose-Robust Face Recognition via Deep Residual Equivariant Mapping"
http://mmlab.ie.cuhk.edu.hk/projects/DREAM/
BSD 2-Clause "Simplified" License
388 stars 98 forks source link

How to get frontal_list_nonli.txt in eval_cfp.py? What are the means of last three values in estimate_pose.txt? #36

Closed LaviLiu closed 5 years ago

LaviLiu commented 5 years ago

Thank you for your code. I have some problems when I read the code:

  1. I canot find frontal_list_nonli.txt and profile_list_nonli.txt which are used in eval_cfp.py. I want to know how to generate them?
  2. I can get estimate_pose.txt by running. The items in estimate_pose.txt are like follows: ../../data/CFP/data/50_Cent/frontal/01.jpg 23.3769 1.43566 178.145 ../../data/CFP/data/50_Cent/frontal/02.jpg -7.93511 1.74187 -4.55453 I want to know the means of the last three values.
jnulzl commented 5 years ago

@Laviyy For 1 , see readme "unzip CFP_protocol.zip" and then you can get it! For 2, i guess three values are pitch,yaw,roll respectively.

LaviLiu commented 5 years ago

@jnulzl Thank you very much. I have got the frontal_list_nonli.txt, but I still have other problems. Do you know how to transform linear yaw in estimate_pose.txt to nonlinear yaw in frontal_list_nonli.txt and profile_list_nonli.txt. Are the following steps correct？

  1. Transform the yaw in estimate_pose.txt to radian unit.
  2. Input the radian yaw to σ(4/pi*radian_yaw -1) will get nonlinear yaw.
jnulzl commented 5 years ago

I guess you are right,refer to "src/stitching/branch_util.py"

def sigmoid(x):
    return 1 / (1 + math.exp(-x))

def norm_angle(angle):
    norm_angle = sigmoid(10 * (abs(angle) / 45.0 - 1))
    return norm_angle
LaviLiu commented 5 years ago

@jnulzl Thank you, I found the code.