（测试版）BERT 动态量化

pipinstallsklearn
pipinstalltransformers==4.29.2

yesy|pipuninstalltorchtorchvision
yesy|pipinstall--pretorch-fhttps://download.pytorch.org/whl/nightly/cu101/torch_nightly.html

importlogging
importnumpyasnp
importos
importrandom
importsys
importtime
importtorch

fromargparseimport Namespace
fromtorch.utils.dataimport (DataLoader, RandomSampler, SequentialSampler,
                              TensorDataset)
fromtqdmimport tqdm
fromtransformersimport (BertConfig, BertForSequenceClassification, BertTokenizer,)
fromtransformersimport glue_compute_metrics as compute_metrics
fromtransformersimport glue_output_modes as output_modes
fromtransformersimport glue_processors as processors
fromtransformersimport glue_convert_examples_to_features as convert_examples_to_features

# Setup logging
logger = logging.getLogger(__name__)
logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
                    datefmt = '%m/%d/%Y %H:%M:%S',
                    level = logging.WARN)

logging.getLogger("transformers.modeling_utils").setLevel(
   logging.WARN)  # Reduce logging

print(torch.__version__)

torch.set_num_threads(1)
print(torch.__config__.parallel_info())

pythondownload_glue_data.py--data_dir='glue_data'--tasks='MRPC'

configs = Namespace()

# The output directory for the fine-tuned model, $OUT_DIR.
configs.output_dir = "./MRPC/"

# The data directory for the MRPC task in the GLUE benchmark, $GLUE_DIR/$TASK_NAME.
configs.data_dir = "./glue_data/MRPC"

# The model name or path for the pre-trained model.
configs.model_name_or_path = "bert-base-uncased"
# The maximum length of an input sequence
configs.max_seq_length = 128

# Prepare GLUE task.
configs.task_name = "MRPC".lower()
configs.processor = processors[configs.task_name]()
configs.output_mode = output_modes[configs.task_name]
configs.label_list = configs.processor.get_labels()
configs.model_type = "bert".lower()
configs.do_lower_case = True

# Set the device, batch size, topology, and caching flags.
configs.device = "cpu"
configs.per_gpu_eval_batch_size = 8
configs.n_gpu = 0
configs.local_rank = -1
configs.overwrite_cache = False


# Set random seed for reproducibility.
defset_seed(seed):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
set_seed(42)

tokenizer = BertTokenizer.from_pretrained(
    configs.output_dir, do_lower_case=configs.do_lower_case)

model = BertForSequenceClassification.from_pretrained(configs.output_dir)
model.to(configs.device)

# coding=utf-8
# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION.  All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

defevaluate(args, model, tokenizer, prefix=""):
    # Loop to handle MNLI double evaluation (matched, mis-matched)
    eval_task_names = ("mnli", "mnli-mm") if args.task_name == "mnli" else (args.task_name,)
    eval_outputs_dirs = (args.output_dir, args.output_dir + '-MM') if args.task_name == "mnli" else (args.output_dir,)

    results = {}
    for eval_task, eval_output_dir in zip(eval_task_names, eval_outputs_dirs):
        eval_dataset = load_and_cache_examples(args, eval_task, tokenizer, evaluate=True)

        if not os.path.exists(eval_output_dir) and args.local_rank in [-1, 0]:
            os.makedirs(eval_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(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 eval
        if args.n_gpu > 1:
            model = torch.nn.DataParallel(model)

        # Eval!
        logger.info("***** Running evaluation {} *****".format(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
        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],
                          'labels':         batch[3]}
                if args.model_type != 'distilbert':
                    inputs['token_type_ids'] = batch[2] if args.model_type in ['bert', 'xlnet'] else None  # XLM, DistilBERT and RoBERTa don't use segment_ids
                outputs = model(**inputs)
                tmp_eval_loss, logits = outputs[:2]

                eval_loss += tmp_eval_loss.mean().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
        if args.output_mode == "classification":
            preds = np.argmax(preds, axis=1)
        elif args.output_mode == "regression":
            preds = np.squeeze(preds)
        result = compute_metrics(eval_task, preds, out_label_ids)
        results.update(result)

        output_eval_file = os.path.join(eval_output_dir, prefix, "eval_results.txt")
        with open(output_eval_file, "w") as writer:
            logger.info("***** Eval results {} *****".format(prefix))
            for key in sorted(result.keys()):
                logger.info("  %s = %s", key, str(result[key]))
                writer.write("%s = %s\n" % (key, str(result[key])))

    return results


defload_and_cache_examples(args, task, tokenizer, evaluate=False):
    if args.local_rank not in [-1, 0] and not evaluate:
        torch.distributed.barrier()  # Make sure only the first process in distributed training process the dataset, and the others will use the cache

    processor = processors[task]()
    output_mode = output_modes[task]
    # Load data features from cache or dataset file
    cached_features_file = os.path.join(args.data_dir, 'cached_{}_{}_{}_{}'.format(
        'dev' if evaluate else 'train',
        list(filter(None, args.model_name_or_path.split('/'))).pop(),
        str(args.max_seq_length),
        str(task)))
    if os.path.exists(cached_features_file) and not args.overwrite_cache:
        logger.info("Loading features from cached file %s", cached_features_file)
        features = torch.load(cached_features_file)
    else:
        logger.info("Creating features from dataset file at %s", args.data_dir)
        label_list = processor.get_labels()
        if task in ['mnli', 'mnli-mm'] and args.model_type in ['roberta']:
            # HACK(label indices are swapped in RoBERTa pretrained model)
            label_list[1], label_list[2] = label_list[2], label_list[1]
        examples = processor.get_dev_examples(args.data_dir) if evaluate else processor.get_train_examples(args.data_dir)
        features = convert_examples_to_features(examples,
                                                tokenizer,
                                                label_list=label_list,
                                                max_length=args.max_seq_length,
                                                output_mode=output_mode,
                                                pad_on_left=bool(args.model_type in ['xlnet']),                 # pad on the left for xlnet
                                                pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
                                                pad_token_segment_id=4 if args.model_type in ['xlnet'] else 0,
        )
        if args.local_rank in [-1, 0]:
            logger.info("Saving features into cached file %s", cached_features_file)
            torch.save(features, cached_features_file)

    if args.local_rank == 0 and not evaluate:
        torch.distributed.barrier()  # Make sure only the first process in distributed training process the dataset, and the others will use the cache

    # Convert to Tensors and build dataset
    all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long)
    all_attention_mask = torch.tensor([f.attention_mask for f in features], dtype=torch.long)
    all_token_type_ids = torch.tensor([f.token_type_ids for f in features], dtype=torch.long)
    if output_mode == "classification":
        all_labels = torch.tensor([f.label for f in features], dtype=torch.long)
    elif output_mode == "regression":
        all_labels = torch.tensor([f.label for f in features], dtype=torch.float)

    dataset = TensorDataset(all_input_ids, all_attention_mask, all_token_type_ids, all_labels)
    return dataset

defprint_size_of_model(model):
    torch.save(model.state_dict(), "temp.p")
    print('Size (MB):', os.path.getsize("temp.p")/1e6)
    os.remove('temp.p')

print_size_of_model(model)
print_size_of_model(quantized_model)

deftime_model_evaluation(model, configs, tokenizer):
    eval_start_time = time.time()
    result = evaluate(configs, model, tokenizer, prefix="")
    eval_end_time = time.time()
    eval_duration_time = eval_end_time - eval_start_time
    print(result)
    print("Evaluate total time (seconds): {0:.1f}".format(eval_duration_time))

# Evaluate the original FP32 BERT model
time_model_evaluation(model, configs, tokenizer)

# Evaluate the INT8 BERT model after the dynamic quantization
time_model_evaluation(quantized_model, configs, tokenizer)

| Prec | F1 score | Model Size | 1 thread | 4 threads |
| FP32 |  0.9019  |   438 MB   | 160 sec  | 85 sec    |
| INT8 |  0.902   |   181 MB   |  90 sec  | 46 sec    |

defids_tensor(shape, vocab_size):
    #  Creates a random int32 tensor of the shape within the vocab size
    return torch.randint(0, vocab_size, shape=shape, dtype=torch.int, device='cpu')

input_ids = ids_tensor([8, 128], 2)
token_type_ids = ids_tensor([8, 128], 2)
attention_mask = ids_tensor([8, 128], vocab_size=2)
dummy_input = (input_ids, attention_mask, token_type_ids)
traced_model = torch.jit.trace(quantized_model, dummy_input)
torch.jit.save(traced_model, "bert_traced_eager_quant.pt")

loaded_quantized_model = torch.jit.load("bert_traced_eager_quant.pt")