I cannot understand why note to exercise 3 says that dense_2_acc_8 is referring to the 7th character output rather than 8th?
"
Thus, dense_2_acc_8: 0.89 means that you are predicting the 7th character of the output correctly 89% of the time in the current batch of data."
what is ense_2_1_accuracy? is it the accuracy for initialisation?
but at the same time, dense_2_9_accuracy is the last one it must be the 10th character?