位置：首页-资讯-后端开发

PythonPaddleNLP实现自动生成虎年藏头诗

2024-04-02 19:55

短信预约 -IT技能 免费直播动态提醒

一、数据处理

本项目中利用古诗数据集作为训练集，编码器接收古诗的每个字的开头，解码器利用编码器的信息生成所有的诗句。为了诗句之间的连贯性，编码器同时也在诗头之前加上之前诗句的信息。举例：

“白日依山尽，黄河入海流，欲穷千里目，更上一层楼。” 可以生成两个样本：

样本一：编码器输入，“白”；解码器输入，“白日依山尽，黄河入海流”

样本二：编码器输入，“白日依山尽，黄河入海流。欲”；解码器输入，“欲穷千里目，更上一层楼。”

1.paddlenlp升级

!pip install -U paddlenlp

Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Collecting paddlenlp
[?25l  Downloading https://pypi.tuna.tsinghua.edu.cn/packages/17/9b/4535ccf0e96c302a3066bd2e4d0f44b6b1a73487c6793024475b48466c32/paddlenlp-2.2.3-py3-none-any.whl (1.2MB)
[K     |████████████████████████████████| 1.2MB 11.2MB/s eta 0:00:01
[?25hRequirement already satisfied, skipping upgrade: h5py in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlenlp) (2.9.0)
Requirement already satisfied, skipping upgrade: colorlog in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlenlp) (4.1.0)
Requirement already satisfied, skipping upgrade: colorama in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlenlp) (0.4.4)
Requirement already satisfied, skipping upgrade: seqeval in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlenlp) (1.2.2)
Requirement already satisfied, skipping upgrade: jieba in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlenlp) (0.42.1)
Requirement already satisfied, skipping upgrade: multiprocess in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlenlp) (0.70.11.1)
Requirement already satisfied, skipping upgrade: six in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from h5py->paddlenlp) (1.16.0)
Requirement already satisfied, skipping upgrade: numpy>=1.7 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from h5py->paddlenlp) (1.20.3)
Requirement already satisfied, skipping upgrade: scikit-learn>=0.21.3 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from seqeval->paddlenlp) (0.24.2)
Requirement already satisfied, skipping upgrade: dill>=0.3.3 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from multiprocess->paddlenlp) (0.3.3)
Requirement already satisfied, skipping upgrade: scipy>=0.19.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from scikit-learn>=0.21.3->seqeval->paddlenlp) (1.6.3)
Requirement already satisfied, skipping upgrade: threadpoolctl>=2.0.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from scikit-learn>=0.21.3->seqeval->paddlenlp) (2.1.0)
Requirement already satisfied, skipping upgrade: joblib>=0.11 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from scikit-learn>=0.21.3->seqeval->paddlenlp) (0.14.1)
Installing collected packages: paddlenlp
  Found existing installation: paddlenlp 2.1.1
    Uninstalling paddlenlp-2.1.1:
      Successfully uninstalled paddlenlp-2.1.1
Successfully installed paddlenlp-2.2.3

2.提取诗头

import re
poems_file = open("./data/data70759/poems_zh.txt", encoding="utf8")
# 对读取的每一行诗句，统计每一句的词头
poems_samples = []
poems_prefix = []
poems_heads = []
for line in poems_file.readlines():
    line_ = re.sub('。', ' ', line)
    line_ = line_.split()
    # 生成训练样本
    for i, p in enumerate(line_):
        poems_heads.append(p[0])
        poems_prefix.append('。'.join(line_[:i]))
        poems_samples.append(p + '。')


# 输出文件信息
for i in range(20):
    print("poems heads:{}, poems_prefix: {}, poems:{}".format(poems_heads[i], poems_prefix[i], poems_samples[i]))

poems heads:欲, poems_prefix: , poems:欲出未出光辣达，千山万山如火发。
poems heads:须, poems_prefix: 欲出未出光辣达，千山万山如火发, poems:须臾走向天上来，逐却残星赶却月。
poems heads:未, poems_prefix: , poems:未离海底千山黑，才到天中万国明。
poems heads:满, poems_prefix: , poems:满目江山四望幽，白云高卷嶂烟收。
poems heads:日, poems_prefix: 满目江山四望幽，白云高卷嶂烟收, poems:日回禽影穿疏木，风递猿声入小楼。
poems heads:远, poems_prefix: 满目江山四望幽，白云高卷嶂烟收。日回禽影穿疏木，风递猿声入小楼, poems:远岫似屏横碧落，断帆如叶截中流。
poems heads:片, poems_prefix: , poems:片片飞来静又闲，楼头江上复山前。
poems heads:飘, poems_prefix: 片片飞来静又闲，楼头江上复山前, poems:飘零尽日不归去，帖破清光万里天。
poems heads:因, poems_prefix: , poems:因登巨石知来处，勃勃元生绿藓痕。
poems heads:静, poems_prefix: 因登巨石知来处，勃勃元生绿藓痕, poems:静即等闲藏草木，动时顷刻徧乾坤。
poems heads:横, poems_prefix: 因登巨石知来处，勃勃元生绿藓痕。静即等闲藏草木，动时顷刻徧乾坤, poems:横天未必朋元恶，捧日还曾瑞至尊。
poems heads:不, poems_prefix: 因登巨石知来处，勃勃元生绿藓痕。静即等闲藏草木，动时顷刻徧乾坤。横天未必朋元恶，捧日还曾瑞至尊, poems:不独朝朝在巫峡，楚王何事谩劳魂。
poems heads:若, poems_prefix: , poems:若教作镇居中国，争得泥金在泰山。
poems heads:才, poems_prefix: , poems:才闻暖律先偷眼，既待和风始展眉。
poems heads:嚼, poems_prefix: , poems:嚼处春冰敲齿冷，咽时雪液沃心寒。
poems heads:蒙, poems_prefix: , poems:蒙君知重惠琼实，薄起金刀钉玉深。
poems heads:深, poems_prefix: , poems:深妆玉瓦平无垅，乱拂芦花细有声。
poems heads:片, poems_prefix: , poems:片逐银蟾落醉觥。
poems heads:巧, poems_prefix: , poems:巧剪银花乱，轻飞玉叶狂。
poems heads:寒, poems_prefix: , poems:寒艳芳姿色尽明。

3.生成词表

# 用PaddleNLP生成词表文件，由于诗文的句式较短，我们以单个字作为词单元生成词表
from paddlenlp.data import Vocab

vocab = Vocab.build_vocab(poems_samples, unk_token="<unk>", pad_token="<pad>", bos_token="<", eos_token=">")
vocab_size = len(vocab)

print("vocab size", vocab_size)
print("word to idx:", vocab.token_to_idx)

4.定义dataset

# 定义数据读取器
from paddle.io import Dataset, BatchSampler, DataLoader
import numpy as np

class PoemDataset(Dataset):
    def __init__(self, poems_data, poems_heads, poems_prefix, vocab, encoder_max_len=128, decoder_max_len=32):
        super(PoemDataset, self).__init__()
        self.poems_data = poems_data
        self.poems_heads = poems_heads
        self.poems_prefix = poems_prefix
        self.vocab = vocab
        self.tokenizer = lambda x: [vocab.token_to_idx[x_] for x_ in x]
        self.encoder_max_len = encoder_max_len
        self.decoder_max_len = decoder_max_len

    def __getitem__(self, idx):
        eos_id = vocab.token_to_idx[vocab.eos_token]
        bos_id = vocab.token_to_idx[vocab.bos_token]
        pad_id = vocab.token_to_idx[vocab.pad_token]
        # 确保encoder和decoder的输出都小于最大长度
        poet = self.poems_data[idx][:self.decoder_max_len - 2]  # -2 包含bos_id和eos_id
        prefix = self.poems_prefix[idx][- (self.encoder_max_len - 3):]  # -3 包含bos_id, eos_id, 和head的编码
        # 对输入输出编码

        sample = [bos_id] + self.tokenizer(poet) + [eos_id]
        prefix = self.tokenizer(prefix) if prefix else []
        heads = prefix + [bos_id] + self.tokenizer(self.poems_heads[idx]) + [eos_id] 
        sample_len = len(sample)
        heads_len = len(heads)
        sample = sample + [pad_id] * (self.decoder_max_len - sample_len)
        heads = heads + [pad_id] * (self.encoder_max_len - heads_len)
        mask = [1] * (sample_len - 1) + [0] * (self.decoder_max_len - sample_len) # -1 to make equal to out[2]
        out = [np.array(d, "int64") for d in [heads, heads_len, sample, sample, mask]]
        out[2] = out[2][:-1]
        out[3] = out[3][1:, np.newaxis]
        return out

    def shape(self):
        return [([None, self.encoder_max_len], 'int64', 'class="lazy" data-src'),
                ([None, 1], 'int64', 'class="lazy" data-src_length'),
                ([None, self.decoder_max_len - 1],'int64', 'trg')], \
               [([None, self.decoder_max_len - 1, 1], 'int64', 'label'),
                ([None, self.decoder_max_len - 1], 'int64', 'trg_mask')]


    def __len__(self):
        return len(self.poems_data)

dataset = PoemDataset(poems_samples, poems_heads, poems_prefix, vocab)
batch_sampler = BatchSampler(dataset, batch_size=2048)
data_loader = DataLoader(dataset, batch_sampler=batch_sampler)

二、定义模型并训练

1.模型定义

from Seq2Seq.models import Seq2SeqModel
from paddlenlp.metrics import Perplexity
from Seq2Seq.loss import CrossEntropyCriterion
import paddle
from paddle.static import InputSpec

# 参数
lr = 1e-6
max_epoch = 20
models_save_path = "./checkpoints"

encoder_attrs = {"vocab_size": vocab_size, "embed_dim": 200, "hidden_size": 128, "num_layers": 4, "dropout": .2,
                    "direction": "bidirectional", "mode": "GRU"}
decoder_attrs = {"vocab_size": vocab_size, "embed_dim": 200, "hidden_size": 128, "num_layers": 4, "direction": "forward",
                    "dropout": .2, "mode": "GRU", "use_attention": True}

# inputs shape and label shape
inputs_shape, labels_shape = dataset.shape()
inputs_list = [InputSpec(input_shape[0], input_shape[1], input_shape[2]) for input_shape in inputs_shape]
labels_list = [InputSpec(label_shape[0], label_shape[1], label_shape[2]) for label_shape in labels_shape]

net = Seq2SeqModel(encoder_attrs, decoder_attrs)
model = paddle.Model(net, inputs_list, labels_list)

model.load("./final_models/model")

opt = paddle.optimizer.Adam(learning_rate=lr, parameters=model.parameters())

model.prepare(opt, CrossEntropyCriterion(), Perplexity())

W0122 21:03:30.616776   166 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0122 21:03:30.620450   166 device_context.cc:465] device: 0, cuDNN Version: 7.6.

2.模型训练

# 训练，训练时间较长，已提供了训练好的模型（./final_models/model）
model.fit(train_data=data_loader, epochs=max_epoch, eval_freq=1, save_freq=5, save_dir=models_save_path, shuffle=True)

3.模型保存

# 保存
model.save("./final_models/model")

三、生成藏头诗

import warnings

def post_process_seq(seq, bos_idx, eos_idx, output_bos=False, output_eos=False):
    """
    Post-process the decoded sequence.
    """
    eos_pos = len(seq) - 1
    for i, idx in enumerate(seq):
        if idx == eos_idx:
            eos_pos = i
            break
    seq = [idx for idx in seq[:eos_pos + 1]
           if (output_bos or idx != bos_idx) and (output_eos or idx != eos_idx)]
    return seq

# 定义用于生成祝福语的类
from paddlenlp.data.tokenizer import JiebaTokenizer

class GenPoems():
    # content (str): the str to generate poems, like "恭喜发财"
    # vocab: the instance of paddlenlp.data.vocab.Vocab
    # model: the Inference Model
    def __init__(self, vocab, model):
        self.bos_id = vocab.token_to_idx[vocab.bos_token]
        self.eos_id = vocab.token_to_idx[vocab.eos_token]
        self.pad_id = vocab.token_to_idx[vocab.pad_token]
        self.tokenizer = lambda x: [vocab.token_to_idx[x_] for x_ in x]
        self.model = model
        self.vocab = vocab

    def gen(self, content, max_len=128):
        # max_len is the encoder_max_len in Seq2Seq Model.
        out = []
        vocab_list = list(vocab.token_to_idx.keys())
        for w in content:
            if w in vocab_list:
                content = re.sub("([。，])", '', content)
                heads = out[- (max_len - 3):] + [self.bos_id] + self.tokenizer(w) + [self.eos_id]
                len_heads = len(heads)
                heads = heads + [self.pad_id] * (max_len - len_heads)
                x = paddle.to_tensor([heads], dtype="int64")
                len_x = paddle.to_tensor([len_heads], dtype='int64')
                pred = self.model.predict_batch(inputs = [x, len_x])[0]
                out += self._get_results(pred)[0]
            else:
                warnings.warn("{} is not in vocab list, so it is skipped.".format(w))
                pass
        out = ''.join([self.vocab.idx_to_token[id] for id in out])
        return out
    
    def _get_results(self, pred):
        pred = pred[:, :, np.newaxis] if len(pred.shape) == 2 else pred
        pred = np.transpose(pred, [0, 2, 1])
        outs = []
        for beam in pred[0]:
            id_list = post_process_seq(beam, self.bos_id, self.eos_id)
            outs.append(id_list)
        return outs

# 载入预测模型
from Seq2Seq.models import Seq2SeqInferModel
import paddle

encoder_attrs = {"vocab_size": vocab_size, "embed_dim": 200, "hidden_size": 128, "num_layers": 4, "dropout": .2,
                    "direction": "bidirectional", "mode": "GRU"}
decoder_attrs = {"vocab_size": vocab_size, "embed_dim": 200, "hidden_size": 128, "num_layers": 4, "direction": "forward",
                    "dropout": .2, "mode": "GRU", "use_attention": True}

infer_model = paddle.Model(Seq2SeqInferModel(encoder_attrs,
                                             decoder_attrs,
                                             bos_id=vocab.token_to_idx[vocab.bos_token],
                                             eos_id=vocab.token_to_idx[vocab.eos_token],
                                             beam_size=10,
                                             max_out_len=256))
infer_model.load("./final_models/model")

# 送新年祝福
# 当然，表白也可以
generator = GenPoems(vocab, infer_model)

content = "生龙活虎"
poet = generator.gen(content)
for line in poet.strip().split('。'):
    try:
        print("{}\t{}。".format(line[0], line))
    except:
        pass

输出结果