def evaluate()

in biolm/run_sequence_labelling.py [0:0]

• 55 lines of code
• 8 McCabe index (conditional complexity)

def evaluate(args, model, tokenizer, labels, pad_token_label_id, mode, prefix=""):
    eval_dataset = load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, mode=mode)

    args.eval_batch_size = args.per_gpu_eval_batch_size * max(1, args.n_gpu)
    # Note that DistributedSampler samples randomly
    eval_sampler = SequentialSampler(eval_dataset) if args.local_rank == -1 else DistributedSampler(eval_dataset)
    eval_dataloader = DataLoader(eval_dataset, sampler=eval_sampler, batch_size=args.eval_batch_size)

    # multi-gpu evaluate
    if args.n_gpu > 1:
        model = torch.nn.DataParallel(model)

    # Eval!
    logger.info("***** Running evaluation %s *****", prefix)
    logger.info("  Num examples = %d", len(eval_dataset))
    logger.info("  Batch size = %d", args.eval_batch_size)
    eval_loss = 0.0
    nb_eval_steps = 0
    preds = None
    out_label_ids = None
    model.eval()
    for batch in tqdm(eval_dataloader, desc="Evaluating"):
        batch = tuple(t.to(args.device) for t in batch)

        with torch.no_grad():
            inputs = {"input_ids": batch[0], "attention_mask": batch[1], "labels": batch[3]}
            if args.model_type != "distilbert":
                inputs["token_type_ids"] = (
                    batch[2] if args.model_type in ["bert", "xlnet"] else None
                )  # XLM and RoBERTa don"t use segment_ids
            outputs = model(**inputs)
            tmp_eval_loss, logits = outputs[:2]

            if args.n_gpu > 1:
                tmp_eval_loss = tmp_eval_loss.mean()  # mean() to average on multi-gpu parallel evaluating

            eval_loss += tmp_eval_loss.item()
        nb_eval_steps += 1
        if preds is None:
            preds = logits.detach().cpu().numpy()
            out_label_ids = inputs["labels"].detach().cpu().numpy()
        else:
            preds = np.append(preds, logits.detach().cpu().numpy(), axis=0)
            out_label_ids = np.append(out_label_ids, inputs["labels"].detach().cpu().numpy(), axis=0)

    eval_loss = eval_loss / nb_eval_steps
    preds = np.argmax(preds, axis=2)

    label_map = {i: label for i, label in enumerate(labels)}

    out_label_list = [[] for _ in range(out_label_ids.shape[0])]
    preds_list = [[] for _ in range(out_label_ids.shape[0])]

    for i in range(out_label_ids.shape[0]):
        for j in range(out_label_ids.shape[1]):
            if out_label_ids[i, j] != pad_token_label_id:
                out_label_list[i].append(label_map[out_label_ids[i][j]])
                preds_list[i].append(label_map[preds[i][j]])

    results = {
        "loss": eval_loss,
        "precision": precision_score(out_label_list, preds_list),
        "recall": recall_score(out_label_list, preds_list),
        "f1": f1_score(out_label_list, preds_list),
    }

    logger.info("***** Eval results %s *****", prefix)
    for key in sorted(results.keys()):
        logger.info("  %s = %s", key, str(results[key]))

    return results, preds_list, out_label_list