PRNet icon indicating copy to clipboard operation
PRNet copied to clipboard

I validated the model on aflw2000-3d database, get bigger NME.

Open lijie2160 opened this issue 4 years ago • 10 comments

the result is: [ 0, 30] Mean: 7.839, Std: 2.902 [30, 60] Mean: 9.314, Std: 4.167 [60, 90] Mean: 13.345, Std: 8.840 [ 0, 90] Mean: 10.166, Std: 2.327

is bigger than the paper mentioned.

lijie2160 avatar Jul 09 '20 09:07 lijie2160

hi , could you tell me how to calculate 3D NME?I don't know when I calculate 3D NME,how can I get bbox. bbox_size = torch.sqrt((right - left) * (bottom - top)) is right?

Shiyu555 avatar Nov 19 '20 11:11 Shiyu555

hi , could you tell me how to calculate 3D NME?I don't know when I calculate 3D NME,how can I get bbox. bbox_size = torch.sqrt((right - left) * (bottom - top)) is right?

i have the same question withyou, how to calculate NME?that makes me big head hhhh:)

Nancyh-e avatar Mar 25 '21 09:03 Nancyh-e

@Shiyu555 @Nancyh-e HERE: https://github.com/cleardusk/3DDFA/blob/master/benchmark_aflw.py

lijie2160 avatar Mar 30 '21 08:03 lijie2160

@Shiyu555 @Nancyh-e HERE: https://github.com/cleardusk/3DDFA/blob/master/benchmark_aflw.py

ok! I'll try it! thanks a lot!Have a great day!!! :)

Nancyh-e avatar Mar 30 '21 09:03 Nancyh-e

@Shiyu555 @Nancyh-e HERE: https://github.com/cleardusk/3DDFA/blob/master/benchmark_aflw.py

hi,I am sorry to bother you again,do you get a similar NME result( according to the link method you have sent to me) to the author's PRNet paper? I use the predicted result of 3D model 68 points(from _kpt.txt of some AFLW2000 test images )and ground truth(from AFLW2000 .mat file of pt3d_68), are they correct data to calculate the NME? Really hope to receive your reply. thanks very much! :) My mail box is [email protected] 求大佬回复一下啊啊啊啊 救救孩子

Nancyh-e avatar Mar 30 '21 11:03 Nancyh-e

@Shiyu555 @Nancyh-e HERE: https://github.com/cleardusk/3DDFA/blob/master/benchmark_aflw.py

hi,I am sorry to bother you again,do you get a similar NME result( according to the link method you have sent to me) to the author's PRNet paper? I use the predicted result of 3D model 68 points(from _kpt.txt of some AFLW2000 test images )and ground truth(from AFLW2000 .mat file of pt3d_68), are they correct data to calculate the NME? Really hope to receive your reply. thanks very much! :) My mail box is [email protected] 求大佬回复一下啊啊啊啊 救救孩子

I wonder what is _ kpt.txt ? The third dimension of position map presents the spatial information ,I calculate NME directly with the predicted position map and the real position map.

Shiyu555 avatar Mar 31 '21 07:03 Shiyu555

@Shiyu555 @Nancyh-e HERE: https://github.com/cleardusk/3DDFA/blob/master/benchmark_aflw.py

hi,I am sorry to bother you again,do you get a similar NME result( according to the link method you have sent to me) to the author's PRNet paper? I use the predicted result of 3D model 68 points(from _kpt.txt of some AFLW2000 test images )and ground truth(from AFLW2000 .mat file of pt3d_68), are they correct data to calculate the NME? Really hope to receive your reply. thanks very much! :) My mail box is [email protected] 求大佬回复一下啊啊啊啊 救救孩子

我只比较的前两维的数据,没有加第三维

lijie2160 avatar Apr 01 '21 08:04 lijie2160

@Shiyu555 @Nancyh-e HERE: https://github.com/cleardusk/3DDFA/blob/master/benchmark_aflw.py

hi,I am sorry to bother you again,do you get a similar NME result( according to the link method you have sent to me) to the author's PRNet paper? I use the predicted result of 3D model 68 points(from _kpt.txt of some AFLW2000 test images )and ground truth(from AFLW2000 .mat file of pt3d_68), are they correct data to calculate the NME? Really hope to receive your reply. thanks very much! :) My mail box is [email protected] 求大佬回复一下啊啊啊啊 救救孩子

我只比较的前两维的数据,没有加第三维

大佬,您是咋比较计算的? 我是进行人脸重建运行demo.py,从position map获取了三维数据点存进了.txt文件,然后和AFLW2000数据集的.mat文件的三维数据进行比较,但是不是很对,前两维也不对,得不出作者的结果,可以指点一下吗?大佬方便留下联系方式吗,啊啊啊这个困扰我好久了!万分感谢!

Nancyh-e avatar Apr 02 '21 03:04 Nancyh-e

@Shiyu555 @Nancyh-e HERE: https://github.com/cleardusk/3DDFA/blob/master/benchmark_aflw.py

hi,I am sorry to bother you again,do you get a similar NME result( according to the link method you have sent to me) to the author's PRNet paper? I use the predicted result of 3D model 68 points(from _kpt.txt of some AFLW2000 test images )and ground truth(from AFLW2000 .mat file of pt3d_68), are they correct data to calculate the NME? Really hope to receive your reply. thanks very much! :) My mail box is [email protected] 求大佬回复一下啊啊啊啊 救救孩子

I wonder what is _ kpt.txt ? The third dimension of position map presents the spatial information ,I calculate NME directly with the predicted position map and the real position map.

it is a txt file to put the 3D 68 points predict datas from position map(in demo.py can find it). and how to use the predicted position map and the real position map to calculate NME directly ? Did you get a similar result to author?thanks a lot, hope your relpy!!!

Nancyh-e avatar Apr 02 '21 03:04 Nancyh-e

@lijie2160 @Nancyh-e hii, could you please send the NMEevaluation code that you have written to me. I have tried it, but there are still errors. thank you My mail box is [email protected]

rakacendekia avatar Apr 23 '21 13:04 rakacendekia