fengju514 / Face-Pose-Net

Estimate 3D face pose (6DoF) or 11 parameters of 3x4 projection matrix by a Convolutional Neural Network

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

how to convert the result to angle ?

translatorgoogle opened this issue · comments

the results printed by your code is:
Model restored.
Predicted pose for: subject10_a
[ 8.27930197e-02 1.95288494e-01 1.03690195e+00 -1.98086071e+01
8.39025688e+00 3.26982227e+03]
Predicted pose for: subject10_a_flip
[ 1.37187794e-01 -1.48106769e-01 -1.06753802e+00 2.50120773e+01
4.28642845e+00 3.29182764e+03]

then how to convert the results to raw,roll,and pitch angle?
much thx:)

The first three elements as shown in the results are already pitch, yaw, and roll angle (in the unit of radian).

I want you to help me confirm the order of pitch, yaw and roll, which is the first, which the second and which the third? thx:)

The order is pitch, yaw, and roll

Model restored.
Predicted pose for: subject10_a
Predicted pose for: subject10_a_flip
Predicted pose for: subject3_a
Predicted pose for: subject3_a_flip
Predicted pose for: subject6_a
Predicted pose for: subject6_a_flip
Predicted pose for: subject8_a
Predicted pose for: subject8_a_flip
Predicted pose for: subject4_a
Predicted pose for: subject4_a_flip
Predicted pose for: subject7_a
Predicted pose for: subject7_a_flip
Predicted pose for: subject9_a
Predicted pose for: subject9_a_flip
Predicted pose for: subject5_a
Predicted pose for: subject5_a_flip
Predicted pose for: subject1_a
Predicted pose for: subject1_a_flip
Predicted pose for: subject2_a
Predicted pose for: subject2_a_flip

Yaw value mean: 6.99341473215
Looking at file: ./tmp/subject10_a.jpg with model3D_aug_-00_00_10.mat
Using pose model in model3D_aug_-00_00_10.mat
Query image shape: (227, 227, 3)
Looking at file: ./tmp/subject10_a.jpg with model3D_aug_-22_00_10.mat
Using pose model in model3D_aug_-22_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject10_a.jpg with model3D_aug_-40_00_10.mat
Using pose model in model3D_aug_-40_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject10_a.jpg with model3D_aug_-55_00_10.mat
Using pose model in model3D_aug_-55_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject10_a.jpg with model3D_aug_-75_00_10.mat
Using pose model in model3D_aug_-75_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Yaw value mean: 23.9717266464
Looking at file: ./tmp/subject3_a.jpg with model3D_aug_-40_00_10.mat
Using pose model in model3D_aug_-40_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject3_a.jpg with model3D_aug_-55_00_10.mat
Using pose model in model3D_aug_-55_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject3_a.jpg with model3D_aug_-75_00_10.mat
Using pose model in model3D_aug_-75_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Yaw value mean: 25.6346889259
Looking at file: ./tmp/subject6_a.jpg with model3D_aug_-40_00_10.mat
Using pose model in model3D_aug_-40_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject6_a.jpg with model3D_aug_-55_00_10.mat
Using pose model in model3D_aug_-55_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject6_a.jpg with model3D_aug_-75_00_10.mat
Using pose model in model3D_aug_-75_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Yaw value mean: -29.4401957865
Looking at file: ./tmp/subject8_a.jpg with model3D_aug_-40_00_10.mat
Using pose model in model3D_aug_-40_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject8_a.jpg with model3D_aug_-55_00_10.mat
Using pose model in model3D_aug_-55_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject8_a.jpg with model3D_aug_-75_00_10.mat
Using pose model in model3D_aug_-75_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Yaw value mean: -26.8160232163
Looking at file: ./tmp/subject4_a.jpg with model3D_aug_-40_00_10.mat
Using pose model in model3D_aug_-40_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject4_a.jpg with model3D_aug_-55_00_10.mat
Using pose model in model3D_aug_-55_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject4_a.jpg with model3D_aug_-75_00_10.mat
Using pose model in model3D_aug_-75_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Yaw value mean: -9.47109702685
Looking at file: ./tmp/subject7_a.jpg with model3D_aug_-00_00_10.mat
Using pose model in model3D_aug_-00_00_10.mat
Query image shape: (227, 227, 3)
Looking at file: ./tmp/subject7_a.jpg with model3D_aug_-22_00_10.mat
Using pose model in model3D_aug_-22_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject7_a.jpg with model3D_aug_-40_00_10.mat
Using pose model in model3D_aug_-40_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject7_a.jpg with model3D_aug_-55_00_10.mat
Using pose model in model3D_aug_-55_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject7_a.jpg with model3D_aug_-75_00_10.mat
Using pose model in model3D_aug_-75_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Yaw value mean: -25.5160943533
Looking at file: ./tmp/subject9_a.jpg with model3D_aug_-40_00_10.mat
Using pose model in model3D_aug_-40_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject9_a.jpg with model3D_aug_-55_00_10.mat
Using pose model in model3D_aug_-55_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject9_a.jpg with model3D_aug_-75_00_10.mat
Using pose model in model3D_aug_-75_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Yaw value mean: 32.5320004185
Looking at file: ./tmp/subject5_a.jpg with model3D_aug_-40_00_10.mat
Using pose model in model3D_aug_-40_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject5_a.jpg with model3D_aug_-55_00_10.mat
Using pose model in model3D_aug_-55_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject5_a.jpg with model3D_aug_-75_00_10.mat
Using pose model in model3D_aug_-75_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Yaw value mean: 7.65499397088
Looking at file: ./tmp/subject1_a.jpg with model3D_aug_-00_00_10.mat
Using pose model in model3D_aug_-00_00_10.mat
Query image shape: (227, 227, 3)
Looking at file: ./tmp/subject1_a.jpg with model3D_aug_-22_00_10.mat
Using pose model in model3D_aug_-22_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject1_a.jpg with model3D_aug_-40_00_10.mat
Using pose model in model3D_aug_-40_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject1_a.jpg with model3D_aug_-55_00_10.mat
Using pose model in model3D_aug_-55_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject1_a.jpg with model3D_aug_-75_00_10.mat
Using pose model in model3D_aug_-75_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Yaw value mean: 31.204200148
Looking at file: ./tmp/subject2_a.jpg with model3D_aug_-40_00_10.mat
Using pose model in model3D_aug_-40_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject2_a.jpg with model3D_aug_-55_00_10.mat
Using pose model in model3D_aug_-55_00_10.mat
Query image shape: (227, 227, 3)
skipping sym
Looking at file: ./tmp/subject2_a.jpg with model3D_aug_-75_00_10.mat
Using pose model in model3D_aug_-75_00_10.mat
Query image shape: (227, 227, 3)
skipping sym

the results printed above do not show the angle, like [ 8.27930197e-02 1.95288494e-01 1.03690195e+00 -1.98086071e+01 8.39025688e+00 3.26982227e+03] .
why?

I have the same issue, how can i get the result like:
"Model restored.
Predicted pose for: subject10_a
[ 8.27930197e-02 1.95288494e-01 1.03690195e+00 -1.98086071e+01
8.39025688e+00 3.26982227e+03]
Predicted pose for: subject10_a_flip
[ 1.37187794e-01 -1.48106769e-01 -1.06753802e+00 2.50120773e+01
4.28642845e+00 3.29182764e+03]
and so on..."

when running main_fpn.py I currently get:
"Model restored.
Predicted pose for: subject10_a
Predicted pose for: subject10_a_flip
Predicted pose for: subject3_a
Predicted pose for: subject3_a_flip
and so on..."