range of valence and arousal

[saeu5407]

Thank you for your great model.

Is the range of valence and arousal of enot_b0_8_va_mtl.pt [-1 to 1] correct?

Based on the Affectnet dataset, it looks like [-1 to 1], but I want to know the exact range.

Thank you.

[av-savchenko]

Hello! Thanks for this question. In the current implementation (see section "Multi-task: FER+Valence-Arousal" in train_emotions-pytorch.ipynb), the valence and arousal values are unbounded. I tried using tanh or similar activations, but the training was unstable. Hence, it is possible that predicted valence and arousal are out of range [-1;1] but you could simply use something like np.clip to fit them into the range [-1;1]. I should also clarify that valence and arousal were mainly used for multi-task learning to improve the quality of facial expression recognition. Hence, the quality of valence/arousal prediction may be imperfect

[saeu5407]

Thank you. Then, can I understand that the training itself was conducted between [-1, 1], but the result value can be other than that?

[av-savchenko]

Yes, you're correct. However, as most of valence and arousal values in the training set have absolute value significantly lower than 1, I did not notice any cases where the prediction of my network were out of bounds [-1;1]

[saeu5407]

Thank you again for the code and explanation you provided.