Micro-Expression-with-Deep-Learning icon indicating copy to clipboard operation
Micro-Expression-with-Deep-Learning copied to clipboard

Published 20 hours ago • verified publisher icon IcedDoggie

Something wrong with Train_Y, and Test_Y.

Open yaru-zhang opened this issue 6 years ago • 7 comments

I'v found a similar problem when I run the code. Train_X_shape: (237, 9, 150528) Train_Y_shape: (243, 5) Test_X_shape: (9, 9, 150528) Test_Y_shape: (3, 5) X_shape: (2133, 3, 224, 224) y_shape: (2187, 5) test_X_shape: (81, 3, 224, 224) test_y_shape: (27, 5) and I guess the problem may be caused by Test_Y, for Test_Y_shape is always (3,5) whatever the ignored files are. Another thing worth mentioning is 243-237=6 while 9-3=6, Train_Y_shape(234) seems to have 6 samples in Test_Y_shape. Can you give me some suggestion? Looking forward for your reply sincerely.

yaru-zhang avatar Jun 20 '18 10:06 yaru-zhang

For datasets: CASME2_Optical has 9 photos in subXX/EPXX files while CASME2_TIM10 and CASME2_Strain_TIM10 has 10 photos in that. Is that OK when I run your code?

yaru-zhang avatar Jun 20 '18 11:06 yaru-zhang

Hi. Apologize for the late reply. Can you try re-running with the latest code? for datasets: all of them must have same length. if CASME2_Optical has 9 photos then all other DBs must have 9 photos.

IcedDoggie avatar Jul 05 '18 04:07 IcedDoggie

https://github.com/IcedDoggie/Micro-Expression-with-Deep-Learning/issues/5

IcedDoggie avatar Jul 05 '18 04:07 IcedDoggie

what is the dataset of CASME2_Strain_TIM10 for？

gxx101 avatar Aug 06 '18 07:08 gxx101

Train with Optical_Strain only.

IcedDoggie avatar Aug 06 '18 07:08 IcedDoggie

Thanks for your reply,but i don't kown that the process of preprocessing if i use my data.

gxx101 avatar Aug 06 '18 08:08 gxx101

hi，i want to ask for what is use for CASME2-ObjectiveClasses.xlsx,?

gxx101 avatar Aug 20 '18 06:08 gxx101