如何在CentOS上利用PyTorch进行自然语言处理

sudo yum install python3 python3-pip

python3 -m venv myenv
source myenv/bin/activate

pip install torch torchvision torchaudio

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

pip install transformers nltk spacy

import nltk
nltk.download('punkt') # 或其他所需的数据包

from transformers import BertTokenizer, BertModel

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertModel.from_pretrained('bert-base-uncased')

import torch
from transformers import BertTokenizer, BertForSequenceClassification
from torch.utils.data import DataLoader, TensorDataset

# 示例数据
texts = ["This is a positive sentence.", "This is a negative sentence."]
labels = [1, 0]  # 1: positive, 0: negative

# 分词
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
encoded_inputs = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')

# 创建数据集和数据加载器
dataset = TensorDataset(encoded_inputs['input_ids'], encoded_inputs['attention_mask'], torch.tensor(labels))
dataloader = DataLoader(dataset, batch_size=2)

# 加载模型
model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

# 优化器 (示例)
optimizer = torch.optim.AdamW(model.parameters(), lr=5e-5)

# 训练 (简化版，实际训练需要更多迭代和评估)
model.train()
for batch in dataloader:
    input_ids, attention_mask, labels = batch
    input_ids, attention_mask, labels = input_ids.to(device), attention_mask.to(device), labels.to(device)
    optimizer.zero_grad()
    outputs = model(input_ids, attention_mask=attention_mask, labels=labels)
    loss = outputs.loss
    loss.backward()
    optimizer.step()

# 保存模型
model.save_pretrained('my_model')
tokenizer.save_pretrained('my_model')

from transformers import BertTokenizer, BertForSequenceClassification

model = BertForSequenceClassification.from_pretrained('my_model')
tokenizer = BertTokenizer.from_pretrained('my_model')

text = "This is a great day!"
encoded_input = tokenizer(text, return_tensors='pt')
model.eval()
with torch.no_grad():
    output = model(**encoded_input)
    prediction = torch.argmax(output.logits, dim=-1)
print(f"Prediction: {prediction.item()}") # 1 for positive, 0 for negative