Closed rockstone533 closed 8 years ago
Why shall we compute "accuracy_class" by the bottom layer be the same "label_class"?
refer to the code in the train/train_val.prototxt:
layers { name: "accuracy_class" type: ACCURACY bottom: "label_class" bottom: "label_class" top: "accuracy_class" }
we can use SilenceLayer as well - it just prevents label_class to be printed in the log file, since it hasn't been used anywhere else.
Why shall we compute "accuracy_class" by the bottom layer be the same "label_class"?
refer to the code in the train/train_val.prototxt: