Hello everyone , I am training a detection model, I want to calculate the hmean , recall, precision of the train data set using the get_metric() function while training the model, please help me

[TranHieu238]

I have seen the train function in the program.py file with code to calculate the accuracy of the train set as follows:

if cal_metric_during_train and epoch % calc_epoch_interval == 0: # only rec and cls need

        batch = [item.numpy() for item in batch]
        if model_type in ['kie', 'sr']:
            eval_class(preds, batch)
        elif model_type in ['table']:
            post_result = post_process_class(preds, batch)
            eval_class(post_result, batch)
        elif algorithm in ['CAN']:
            model_type = 'can'
            eval_class(preds[0], batch[2:], epoch_reset=(idx == 0))
        else:
            if config['Loss']['name'] in ['MultiLoss', 'MultiLoss_v2'
                                          ]:  # for multi head loss
                post_result = post_process_class(
                    preds['ctc'], batch[1])  # for CTC head out
            elif config['Loss']['name'] in ['VLLoss']:
                post_result = post_process_class(preds, batch[1],
                                                 batch[-1])
            else:
                post_result = post_process_class(preds, batch[1])
            eval_class(post_result, batch)
        metric = eval_class.get_metric()
        train_stats.update(metric)

but this code for model rec or cls , so for the detection model, how do I calculate it?