For positive label gamma is being multiplied instead of exponent

[jonesmabea]

In the sigmoid focal loss you have
L=-labels*(1-alpha)*((1-y_pred)*gamma)*tf.log(y_pred)-\ (1-labels)*alpha*(y_pred**gamma)*tf.log(1-y_pred)
instead of
L=-labels*(1-alpha)*((1-y_pred)**gamma)*tf.log(y_pred)-\ (1-labels)*alpha*(y_pred**gamma)*tf.log(1-y_pred)