昇思25天学习打卡营第24天|基于MindSpore通过GPT实现情感分类

今天学习了《基于MindSpore通过GPT实现情感分类》相关内容，这章节内容比较少，主要代码如下：

安装实验环境：

%%capture captured_output
# 实验环境已经预装了mindspore==2.2.14，如需更换mindspore版本，可更改下面mindspore的版本号
!pip uninstall mindspore -y
!pip install -i https://pypi.mirrors.ustc.edu.cn/simple mindspore==2.2.14

安装mindnlp和jieba

# 该案例在 mindnlp 0.3.1 版本完成适配，如果发现案例跑不通，可以指定mindnlp版本，执行`!pip install mindnlp==0.3.1`
!pip install mindnlp
!pip install jieba
%env HF_ENDPOINT=https://hf-mirror.com`

jieba是一个优秀的中文分词第三方库，主要用于Python编程语言中。 它能够帮助用户将中文文本切割成单个的词语，这对于自然语言处理和文本分析尤为重要。jieba库提供了多种分词模式，使得用户可以根据不同的需求选择合适的分词方式。此外，jieba库还支持词频统计、词云图生成以及构建对象等功能，是处理中文文本的一个强大工具。‌

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

导入 mindspore 、mindnlp等框架和库

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

导入数据

imdb_train.get_dataset_size()

运行后输出：25000

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

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)

# 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())

运行后输出：
[Tensor(shape=[4, 512], dtype=Int64, value=
[[ 11, 250, 15 … 3, 242, 3],
[ 5, 23, 5 … 40480, 40480, 40480],
[ 14, 3, 5 … 243, 8, 18073],
[ 7, 250, 3 … 40480, 40480, 40480]]),
Tensor(shape=[4, 512], dtype=Int64, value=
[[1, 1, 1 … 1, 1, 1],
[1, 1, 1 … 0, 0, 0],
[1, 1, 1 … 1, 1, 1],
[1, 1, 1 … 0, 0, 0]]),
Tensor(shape=[4], dtype=Int32, value= [0, 1, 0, 1])]

在这里插入代码片

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")

evaluator = Evaluator(network=model, eval_dataset=dataset_test, metrics=metric)
evaluator.run(tgt_columns="labels")