predict.py

# Copyright (c) 2020 PaddlePaddle Authors. 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.

import argparse
import os
from functools import partial

import numpy as np
import paddle
import paddle.nn.functional as F
import paddlenlp as ppnlp
from paddlenlp.data import Stack, Tuple, Pad

# yapf: disable
parser = argparse.ArgumentParser()
parser.add_argument("--params_path", type=str, required=True, help="The path to model parameters to be loaded.")
parser.add_argument("--max_seq_length", default=128, type=int, help="The maximum total input sequence length after tokenization. "
    "Sequences longer than this will be truncated, sequences shorter will be padded.")
parser.add_argument("--batch_size", default=32, type=int, help="Batch size per GPU/CPU for training.")
parser.add_argument('--device', choices=['cpu', 'gpu', 'xpu'], default="gpu", help="Select which device to train model, defaults to gpu.")
args = parser.parse_args()
# yapf: enable


def convert_example(example,
                    tokenizer,
                    label_list,
                    max_seq_length=512,
                    is_test=False):
    """
    Builds model inputs from a sequence or a pair of sequence for sequence classification tasks
    by concatenating and adding special tokens. And creates a mask from the two sequences passed 
    to be used in a sequence-pair classification task.
        
    A BERT sequence has the following format:

    - single sequence: ``[CLS] X [SEP]``
    - pair of sequences: ``[CLS] A [SEP] B [SEP]``

    A BERT sequence pair mask has the following format:
    ::
        0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
        | first sequence    | second sequence |

    If only one sequence, only returns the first portion of the mask (0's).


    Args:
        example(obj:`list[str]`): List of input data, containing text and label if it have label.
        tokenizer(obj:`PretrainedTokenizer`): This tokenizer inherits from :class:`~paddlenlp.transformers.PretrainedTokenizer` 
            which contains most of the methods. Users should refer to the superclass for more information regarding methods.
        label_list(obj:`list[str]`): All the labels that the data has.
        max_seq_len(obj:`int`): The maximum total input sequence length after tokenization. 
            Sequences longer than this will be truncated, sequences shorter will be padded.
        is_test(obj:`False`, defaults to `False`): Whether the example contains label or not.

    Returns:
        input_ids(obj:`list[int]`): The list of token ids.
        token_type_ids(obj: `list[int]`): List of sequence pair mask.
        label(obj:`numpy.array`, data type of int64, optional): The input label if not is_test.
    """
    encoded_inputs = tokenizer(text=example, max_seq_len=max_seq_length)
    input_ids = encoded_inputs["input_ids"]
    token_type_ids = encoded_inputs["token_type_ids"]

    if not is_test:
        # create label maps
        label_map = {}
        for (i, l) in enumerate(label_list):
            label_map[l] = i

        label = label_map[label]
        label = np.array([label], dtype="int64")
        return input_ids, token_type_ids, label
    else:
        return input_ids, token_type_ids


def predict(model, data, tokenizer, label_map, batch_size=1):
    """
    Predicts the data labels.

    Args:
        model (obj:`paddle.nn.Layer`): A model to classify texts.
        data (obj:`List(Example)`): The processed data whose each element is a Example (numedtuple) object.
            A Example object contains `text`(word_ids) and `seq_len`(sequence length).
        tokenizer(obj:`PretrainedTokenizer`): This tokenizer inherits from :class:`~paddlenlp.transformers.PretrainedTokenizer` 
            which contains most of the methods. Users should refer to the superclass for more information regarding methods.
        label_map(obj:`dict`): The label id (key) to label str (value) map.
        batch_size(obj:`int`, defaults to 1): The number of batch.

    Returns:
        results(obj:`dict`): All the predictions labels.
    """
    examples = []
    for text in data:
        input_ids, token_type_ids = convert_example(
            text,
            tokenizer,
            label_list=label_map.values(),
            max_seq_length=args.max_seq_length,
            is_test=True)
        examples.append((input_ids, token_type_ids))

    # Seperates data into some batches.
    batches = [
        examples[idx:idx + batch_size]
        for idx in range(0, len(examples), batch_size)
    ]
    batchify_fn = lambda samples, fn=Tuple(
        Pad(axis=0, pad_val=tokenizer.pad_token_id),  # input
        Pad(axis=0, pad_val=tokenizer.pad_token_type_id),  # segment
    ): fn(samples)

    results = []
    model.eval()
    for batch in batches:
        input_ids, token_type_ids = batchify_fn(batch)
        input_ids = paddle.to_tensor(input_ids)
        token_type_ids = paddle.to_tensor(token_type_ids)
        logits = model(input_ids, token_type_ids)
        probs = F.softmax(logits, axis=1)
        idx = paddle.argmax(probs, axis=1).numpy()
        idx = idx.tolist()
        labels = [label_map[i] for i in idx]
        results.extend(labels)
    return results


if __name__ == "__main__":
    paddle.set_device(args.device)

    # ErnieTinyTokenizer is special for ernie-tiny pretained model.
    tokenizer = ppnlp.transformers.ErnieTinyTokenizer.from_pretrained(
        'ernie-tiny')

    data = [
        '这个宾馆比较陈旧了，特价的房间也很一般。总体来说一般',
        '怀着十分激动的心情放映，可是看着看着发现，在放映完毕后，出现一集米老鼠的动画片',
        '作为老的四星酒店，房间依然很整洁，相当不错。机场接机服务很好，可以在车上办理入住手续，节省时间。',
    ]
    label_map = {0: 'negative', 1: 'positive'}

    model = ppnlp.transformers.ErnieForSequenceClassification.from_pretrained(
        'ernie-tiny', num_classes=len(label_map))

    if args.params_path and os.path.isfile(args.params_path):
        state_dict = paddle.load(args.params_path)
        model.set_dict(state_dict)
        print("Loaded parameters from %s" % args.params_path)

    results = predict(
        model, data, tokenizer, label_map, batch_size=args.batch_size)
    for idx, text in enumerate(data):
        print('Data: {} \t Lable: {}'.format(text, results[idx]))