def evaluate(args, model, tokenizer, prefix=""):
dataset, examples, features = load_and_cache_examples(args, tokenizer, evaluate=True, output_examples=True)
if not os.path.exists(args.output_dir) and args.local_rank in [-1, 0]:
os.makedirs(args.output_dir)
args.eval_batch_size = args.per_gpu_eval_batch_size * max(1, args.n_gpu)
# Note that DistributedSampler samples randomly
eval_sampler = SequentialSampler(dataset)
eval_dataloader = DataLoader(dataset, sampler=eval_sampler, batch_size=args.eval_batch_size)
# multi-gpu evaluate
if args.n_gpu > 1 and not isinstance(model, torch.nn.DataParallel):
model = torch.nn.DataParallel(model)
# Eval!
logger.info("***** Running evaluation {} *****".format(prefix))
logger.info(" Num examples = %d", len(dataset))
logger.info(" Batch size = %d", args.eval_batch_size)
all_results = []
start_time = timeit.default_timer()
for batch in tqdm(eval_dataloader, desc="Evaluating"):
model.eval()
batch = tuple(t.to(args.device) for t in batch)
with torch.no_grad():
inputs = {
"input_ids": batch[0],
"attention_mask": batch[1],
"token_type_ids": batch[2],
}
if args.model_type in ["xlm", "roberta", "distilbert", "camembert", "bart", "longformer"]:
del inputs["token_type_ids"]
feature_indices = batch[3]
# XLNet and XLM use more arguments for their predictions
if args.model_type in ["xlnet", "xlm"]:
inputs.update({"cls_index": batch[4], "p_mask": batch[5]})
# for lang_id-sensitive xlm models
if hasattr(model, "config") and hasattr(model.config, "lang2id"):
inputs.update(
{"langs": (torch.ones(batch[0].shape, dtype=torch.int64) * args.lang_id).to(args.device)}
)
outputs = model(**inputs)
for i, feature_index in enumerate(feature_indices):
eval_feature = features[feature_index.item()]
unique_id = int(eval_feature.unique_id)
output = [to_list(output[i]) for output in outputs]
# Some models (XLNet, XLM) use 5 arguments for their predictions, while the other "simpler"
# models only use two.
if len(output) >= 5:
start_logits = output[0]
start_top_index = output[1]
end_logits = output[2]
end_top_index = output[3]
cls_logits = output[4]
result = SquadResult(
unique_id,
start_logits,
end_logits,
start_top_index=start_top_index,
end_top_index=end_top_index,
cls_logits=cls_logits,
)
else:
start_logits, end_logits = output
result = SquadResult(unique_id, start_logits, end_logits)
all_results.append(result)
evalTime = timeit.default_timer() - start_time
logger.info(" Evaluation done in total %f secs (%f sec per example)", evalTime, evalTime / len(dataset))
# Compute predictions
output_prediction_file = os.path.join(args.output_dir, "predictions_{}.json".format(prefix))
output_nbest_file = os.path.join(args.output_dir, "nbest_predictions_{}.json".format(prefix))
if args.version_2_with_negative:
output_null_log_odds_file = os.path.join(args.output_dir, "null_odds_{}.json".format(prefix))
else:
output_null_log_odds_file = None
# XLNet and XLM use a more complex post-processing procedure
if args.model_type in ["xlnet", "xlm"]:
start_n_top = model.config.start_n_top if hasattr(model, "config") else model.module.config.start_n_top
end_n_top = model.config.end_n_top if hasattr(model, "config") else model.module.config.end_n_top
predictions = compute_predictions_log_probs(
examples,
features,
all_results,
args.n_best_size,
args.max_answer_length,
output_prediction_file,
output_nbest_file,
output_null_log_odds_file,
start_n_top,
end_n_top,
args.version_2_with_negative,
tokenizer,
args.verbose_logging,
)
else:
predictions = compute_predictions_logits(
examples,
features,
all_results,
args.n_best_size,
args.max_answer_length,
args.do_lower_case,
output_prediction_file,
output_nbest_file,
output_null_log_odds_file,
args.verbose_logging,
args.version_2_with_negative,
args.null_score_diff_threshold,
tokenizer,
)
# Compute the F1 and exact scores.
results = squad_evaluate(examples, predictions)
return results
def evaluate(args, model, tokenizer, prefix=""):
dataset, examples, features = load_and_cache_examples(args,
tokenizer,
evaluate=True,
output_examples=True)
if not os.path.exists(args.output_dir) and args.local_rank in [-1, 0]:
os.makedirs(args.output_dir)
args.eval_batch_size = args.per_gpu_eval_batch_size * max(1, args.n_gpu)
# Note that DistributedSampler samples randomly
eval_sampler = SequentialSampler(dataset)
eval_dataloader = DataLoader(dataset,
sampler=eval_sampler,
batch_size=args.eval_batch_size)
# Eval!
print("***** Running evaluation {} *****".format(prefix))
print(" Num examples = %d", len(dataset))
print(" Batch size = %d", args.eval_batch_size)
all_results = []
start_time = timeit.default_timer()
eval_pbar = tqdm(total=len(dataset),
position=0,
leave=True,
file=sys.stdout,
bar_format="{l_bar}%s{bar}%s{r_bar}" %
(Fore.GREEN, Fore.RESET))
for batch in eval_dataloader:
model.eval()
batch = tuple(t.to(args.device) for t in batch)
with torch.no_grad():
inputs = {
"input_ids": batch[0],
"attention_mask": batch[1],
"token_type_ids": batch[2],
}
feature_indices = batch[3]
outputs = model(**inputs)
for i, feature_index in enumerate(feature_indices):
eval_feature = features[feature_index.item()]
unique_id = int(eval_feature.unique_id)
output = [to_list(output[i]) for output in outputs]
start_logits, end_logits = output
result = SquadResult(unique_id, start_logits, end_logits)
all_results.append(result)
eval_pbar.update(batch[0].size(0)) # hiepnh
eval_pbar.close() # hiepnh
evalTime = timeit.default_timer() - start_time
print(" Evaluation done in total %f secs (%f sec per example)", evalTime,
evalTime / len(dataset))
# Compute predictions
output_prediction_file = os.path.join(args.output_dir,
"predictions_{}.json".format(prefix))
output_nbest_file = os.path.join(
args.output_dir, "nbest_predictions_{}.json".format(prefix))
if args.version_2_with_negative:
output_null_log_odds_file = os.path.join(
args.output_dir, "null_odds_{}.json".format(prefix))
else:
output_null_log_odds_file = None
predictions = compute_predictions_logits(
examples,
features,
all_results,
args.n_best_size,
args.max_answer_length,
args.do_lower_case,
output_prediction_file,
output_nbest_file,
output_null_log_odds_file,
args.verbose_logging,
args.version_2_with_negative,
args.null_score_diff_threshold,
tokenizer,
)
# Compute the F1 and exact scores.
results = squad_evaluate(examples, predictions)
return results
