regress loss error ，is too large, torch is 1.0.1 python 2.7 about accurate-head-pose HOT 6 CLOSED

Just wait for more epochs and check whether the loss decreases, usually, it can converge around 10-15 epoch.

from accurate-head-pose.

@haofanwang
Yes, it can converge, and I test 5epoch.pkl ，the AFLW2000 out as follows:
Test error in degrees of the model on the 1969 test images. Yaw: 5.1895, Pitch: 6.5614, Roll: 5.6367, MAE: 5.7959
the 25 epoch.pkl MAE is 5.8
the out have higher losses than your paper.
What should I pay attention to?
the lr = 0.000001 is your paper sets
batch =32
alpha = 2
dataset = Pose_300W_LP_multi

from accurate-head-pose.

Thanks for following our method . I think initialization may play a role here, so your MAE should be fine. You can also test your saved models one by one to see which outcomes the best performance. Besides, reproduced model is provided, you can test by yourself.

from accurate-head-pose.

@haofanwang ，OK，I will try it. Thanks

from accurate-head-pose.

Closed.

from accurate-head-pose.

I got same problem

from accurate-head-pose.