Hi, Thanks a lot for your sharing! The code have trained and tested in my Server, and there still has a question as,
due to the input size of the vtcnn and mrresnet is fixed to adapt the training data, then if I want to test by using the signal data generated or collected by us, which the length is not the same as the trainning data, how should we do?
cut or sample it?
Thanks a lot~

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

When using torch 2.3.1 and poutyne 1.17.1, I discovered that EpochMetric has been deprecated in poutyne. Upon checking, I found that poutyne has integrated the TopKAccuracy method. Therefore, I was able to successfully train the model by using
from poutyne.framework.metrics import TopKAccuracy.