Loading the saved .csv model file failed if we trained model with more generations than are weights in level L0.
Method in SnakeAI.pde:
void fileSelectedIn(File selection)
157:
while(genscore != 0)
it should be
while((genscore != 0) & (g<modelTable.getRowCount()-1))
E.g. For topology 1x4 we have 25x4 L0 weights => rows in saved output .csv file
If the simulation is performed for more than 100 generations (101) than 100th row in saved .csv file it will have in Graph column genscore<>0 and 101st row will not exist. An error exception will be thrown and the model will not be loaded.
It's just work around. In case we need a Graph of progress, the results of the score per generation should be saved in a separate file.
Loading the saved .csv model file failed if we trained model with more generations than are weights in level L0.
Method in SnakeAI.pde: void fileSelectedIn(File selection)
157: while(genscore != 0)
it should be while((genscore != 0) & (g<modelTable.getRowCount()-1))
E.g. For topology 1x4 we have 25x4 L0 weights => rows in saved output .csv file If the simulation is performed for more than 100 generations (101) than 100th row in saved .csv file it will have in Graph column genscore<>0 and 101st row will not exist. An error exception will be thrown and the model will not be loaded.
It's just work around. In case we need a Graph of progress, the results of the score per generation should be saved in a separate file.