How to interpret results correctly?

[paskalkris]

Hello!
I'm sorry to trouble you. I tried to launch your project, which is on the github (LIVE_CER). For my file, I received the following data:
[array ([[0.09462767, 0.01970773, 0.88566464]], dtype = float32), array ([[0.91368246, 0.00295924, 0.08335838]], dtype = float32)]

please tell me how to interpret them correctly?
I used the following command to run the script:

python ./src/offline_ser.py -d_id 1 -vd 1000 -p_mode 2 -f_mode 1 -log ./output/offline.wav.csv \
       -md ./model/si.ENG.cw.raw.2d.res.lstm.gpool.dnn.1.h5 -c_len 1600 -m_t_step 16000 -tasks 'arousal: 2, valence: 2' --stl \
       --save -wav '../RawData/2.78-7.655-SPK_2.wav'

If I understand correctly, then the first array is responsible for arousal, and the second for valence, but further it is not entirely clear, are these the probabilities of positive, neutral and negative values? If so, in what order are these indicators?

Thank you!