数据导入

import os

import mindspore
from mindspore.dataset import text, GeneratorDataset, transforms
from mindspore import nn

from mindnlp.dataset import load_dataset

from mindnlp._legacy.engine import Trainer, Evaluator
from mindnlp._legacy.engine.callbacks import CheckpointCallback, BestModelCallback
from mindnlp._legacy.metrics import Accuracy

imdb_ds = load_dataset('imdb', split=['train', 'test'])
imdb_train = imdb_ds['train']
imdb_test = imdb_ds['test']

 数据预处理

import numpy as np

def process_dataset(dataset, tokenizer, max_seq_len=512, batch_size=4, shuffle=False):
    is_ascend = mindspore.get_context('device_target') == 'Ascend'
    def tokenize(text):
        if is_ascend:
            tokenized = tokenizer(text, padding='max_length', truncation=True, max_length=max_seq_len)
        else:
            tokenized = tokenizer(text, truncation=True, max_length=max_seq_len)
        return tokenized['input_ids'], tokenized['attention_mask']

    if shuffle:
        dataset = dataset.shuffle(batch_size)

    # map dataset
    dataset = dataset.map(operations=[tokenize], input_columns="text", output_columns=['input_ids', 'attention_mask'])
    dataset = dataset.map(operations=transforms.TypeCast(mindspore.int32), input_columns="label", output_columns="labels")
    # batch dataset
    if is_ascend:
        dataset = dataset.batch(batch_size)
    else:
        dataset = dataset.padded_batch(batch_size, pad_info={'input_ids': (None, tokenizer.pad_token_id),
                                                             'attention_mask': (None, 0)})

    return dataset

加载token

from mindnlp.transformers import GPTTokenizer
# tokenizer
gpt_tokenizer = GPTTokenizer.from_pretrained('openai-gpt')

# add sepcial token: <PAD>
special_tokens_dict = {
    "bos_token": "<bos>",
    "eos_token": "<eos>",
    "pad_token": "<pad>",
}
num_added_toks = gpt_tokenizer.add_special_tokens(special_tokens_dict)

 训练测试数据处理

# split train dataset into train and valid datasets
imdb_train, imdb_val = imdb_train.split([0.7, 0.3])

dataset_train = process_dataset(imdb_train, gpt_tokenizer, shuffle=True)
dataset_val = process_dataset(imdb_val, gpt_tokenizer)
dataset_test = process_dataset(imdb_test, gpt_tokenizer)

next(dataset_train.create_tuple_iterator())

训练代码

from mindnlp.transformers import GPTForSequenceClassification
from mindspore.experimental.optim import Adam

# set bert config and define parameters for training
model = GPTForSequenceClassification.from_pretrained('openai-gpt', num_labels=2)
model.config.pad_token_id = gpt_tokenizer.pad_token_id
model.resize_token_embeddings(model.config.vocab_size + 3)

optimizer = nn.Adam(model.trainable_params(), learning_rate=2e-5)

metric = Accuracy()

# define callbacks to save checkpoints
ckpoint_cb = CheckpointCallback(save_path='checkpoint', ckpt_name='gpt_imdb_finetune', epochs=1, keep_checkpoint_max=2)
best_model_cb = BestModelCallback(save_path='checkpoint', ckpt_name='gpt_imdb_finetune_best', auto_load=True)

trainer = Trainer(network=model, train_dataset=dataset_train,
                  eval_dataset=dataset_train, metrics=metric,
                  epochs=1, optimizer=optimizer, callbacks=[ckpoint_cb, best_model_cb],
                  jit=False)

trainer.run(tgt_columns="labels")

结论

基于gpt来实现文本的情感分类，相较于rnn，lstm等模型的训练方式，在基础之上加入了词向量，考虑到gpt模型体积较大，多数情况下词向量用的是bert的已经训练好的词向量。