You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I found a bug when I tested a trained model. Concretely, this bug exists in function "eval_example". Due to the value of ground truth may be -1, 'yi' may be less than zero in some cases so that 'rec' will be negative. Then I added this code in the function: y_true[y_true == -1.] = 0 and the result was correct.
The text was updated successfully, but these errors were encountered:
I found a bug when I tested a trained model. Concretely, this bug exists in function "eval_example". Due to the value of ground truth may be -1, 'yi' may be less than zero in some cases so that 'rec' will be negative. Then I added this code in the function:
y_true[y_true == -1.] = 0
and the result was correct.The text was updated successfully, but these errors were encountered: