I have a training file for a two class problem and the labels are +1 and -1. After I run svm-train, the model file generated has real valued labels between -2 and +2.
Portion of Training file:
-1 1:-0.0902235 2:0.642459 3:-0.996008 4:-0.990354 5:-0.0415552 6:-0.559606 7:0.481824
-1 1:-0.53561 2:-0.739702 3:0.0719997 4:-0.0874957 5:-0.804345 6:-0.492728 7:-0.192003
1 1:-0.0607377 2:0.621136 3:-0.998019 4:-0.997149 5:0.0494642 6:-0.402682 7:0.128106
Corresponding support vectors in the model file:
-2 1:-0.0902235 2:0.642459 3:-0.996008 4:-0.990354 5:-0.0415552 6:-0.559606 7:0.481824
-0.962578101983108 1:-0.53561 2:-0.739702 3:0.0719997 4:-0.0874957 5:-0.804345 6:-0.492728 7:-0.19200
2 1:-0.0607377 2:0.621136 3:-0.998019 4:-0.997149 5:0.0494642 6:-0.402682 7:0.128106
They are in libsvm format.
I have not been able to figure out why this label alteration happens. Are the support vector labels important for tests?
