ASSMN
ASSMN copied to clipboard
Predicting
why the correct/total is only 14.4476% when Predicting with the previous stored model through infer.py?
why the correct/total is only 14.4476% when Predicting with the previous stored model through infer.py?
Because actually the ground truth doesn't cover all pixels. The infer.py is only used to generate the classification map for viewing. The true accuracy evaluation is achieved with trainval.py.