why do labels have to be reassigned to their original labels at each iteration in filter_relabel
train_batch_data = self.train_dl.datasetfor i in range(len(train_batch_data)):train_batch_data[i][-1][:] = self.ori_train_labels[i]self.train_dl = DataLoader(train_batch_data, batch_size=self.batch_size, sampler=SequentialSampler(train_batch_data))
why do labels have to be reassigned to their original labels at each iteration in filter_relabel
train_batch_data = self.train_dl.datasetfor i in range(len(train_batch_data)):train_batch_data[i][-1][:] = self.ori_train_labels[i]self.train_dl = DataLoader(train_batch_data, batch_size=self.batch_size, sampler=SequentialSampler(train_batch_data))