Closed onepeachbiubiubiu closed 1 year ago
As you said, the accuracy
doesn't backpropagate any gradient; removing it from the training configuration will not affect the training results.
In fact, we just calculate training accuracy like a loss calculation and then write its result into the log files and tensorboard as a monitoring metric.
It seems 'argmax function' in accuracy calculation cannot backpropagate the gradient,so why accuracy be used as loss?