INNER CODE UNIT · Python

_on_epoch_end

lbcb-sci/RiNALMo · train_ncrna_classification.py:92

    def _on_epoch_end(self, split: str):
        preds = []
        labels = []

        for pred, label in self.val_step_outputs:
            preds.append(pred)
            labels.append(label)
        
        preds = torch.cat(preds, dim=0)
        labels = torch.cat(labels, dim=0)

        # calculate F1 score
        preds = preds.cpu().numpy()
        labels = labels.cpu().numpy()

        f1 = f1_score(labels, preds, average='weighted')
        acc = accuracy_score(labels, preds)

View source record →