Bug with early stopping on loss
dfdazac opened this issue · 1 comments
dfdazac commented
Thanks for open sourcing your code!
This line:
Line 262 in 2dbad87
is problematic for some datasets when training with p_val = 0
and p_test = 0
(as in the case of node classification), because the loss might start at values much higher than 1 and it might take more than 100 epochs to reach this value. This means that self.__save_vars()
is never called, so then an exception is raised here:
Line 299 in 2dbad87
because the attribute self.saved_vars
does not exist. I worked around this by changing the first line above to
early_stopping_score_max = -float('inf')
abojchevski commented
Thanks for catching this! I've added the proposed change to the code.