search

microsoft / FERPlus

This is the FER+ new label annotations for the Emotion FER dataset.
https://arxiv.org/abs/1608.01041
Other
594 stars 166 forks source link

Overloaded neutral? #11

Open handav opened 5 years ago

handav commented 5 years ago

With the crossentropy model, performing softmax on the last dense layer, every image seems to have neutral as its highest (99%+) value. Is that in line with your results? Any suggestions for neutralizing neutral?

amirhfarzaneh commented 5 years ago

Do you mean that the network predicts every image in the test set as neutral?

DanielXu123 commented 4 years ago

I do have the same problem, I replace the FER 2013 emotion label with the mostly marked label in FER+, then trained that dataset with MobileNet. I get the model test accuracy with ~80% .

Then I randomly choose multi web downloaded images to run the forward progress. I get most results of neutral while some of the images should be happiness or sad