Can't instantiate abstract class TopKAccuracy with abstract methods reset

[azyslzp]

In the debug of train.py. I met a problem, that is when I run

Metrics

top3 = TopKAccuracy(k=3)
top5 = TopKAccuracy(k=5)
metrics = ["acc", top3, top5]
it comes from
class TopKAccuracy(EpochMetric):
def init(self, k: int):
super(TopKAccuracy, self).init()
self.k = k
self.acc = None
self.name = "top_{}_accuracy".format(self.k)
self.register_buffer("_accuracy", None)
....
but it output TypeError: Can't instantiate abstract class TopKAccuracy with abstract methods reset

[isaaccorley]

Fixed #2

[azyslzp]

Fixed #2

Thanks a lot! I have also solved the problem by comment the
@AbstractMethod