在本次学习中，我们将对具有 6 个类的数据集执行分类。请注意，该数据集实际上并不是情感分析数据集，而是问题数据集，任务是对问题所属的类别进行分类。但是，本次学习中涵盖的所有内容都适用于任何包含属于 𝐶C 类之一的输入序列的示例的数据集。
下面，我们设置字段并加载数据集，与之前不同的是：
第一，我们不需要在 LABEL 字段中设置 dtype。在处理多类问题时，PyTorch 期望标签被数字化为LongTensor。
第二，这次我们使用的是TREC数据集而不是IMDB数据集。 fine_grained 参数允许我们使用细粒度标签（其中有50个类）或不使用（在这种情况下它们将是6个类）。
训练模型代码：
import torch from torchtext.legacy import data from torchtext.legacy import datasets import random SEED = 1234 torch.manual_seed(SEED) torch.backends.cudnn.deterministic = True TEXT = data.Field(tokenize = 'spacy',tokenizer_language = 'en_core_web_sm') LABEL = data.LabelField() train_data, test_data = datasets.TREC.splits(TEXT, LABEL, fine_grained=False) train_data, valid_data = train_data.split(random_state = random.seed(SEED)) # 建立词汇表 MAX_VOCAB_SIZE = 25_000 TEXT.build_vocab(train_data, max_size = MAX_VOCAB_SIZE, vectors = "glove.6B.100d", unk_init = torch.Tensor.normal_) LABEL.build_vocab(train_data) # 建立迭代器 BATCH_SIZE = 64 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') train_iterator, valid_iterator, test_iterator = data.BucketIterator.splits( (train_data, valid_data, test_data), batch_size = BATCH_SIZE, device = device) # 模型的建立 import torch.nn as nn import torch.nn.functional as F class CNN(nn.Module): def __init__(self, vocab_size, embedding_dim, n_filters, filter_sizes, output_dim, dropout, pad_idx): super().__init__() self.embedding = nn.Embedding(vocab_size, embedding_dim) self.convs = nn.ModuleList([ nn.Conv2d(in_channels = 1, out_channels = n_filters, kernel_size = (fs, embedding_dim)) for fs in filter_sizes ]) self.fc = nn.Linear(len(filter_sizes) * n_filters, output_dim) self.dropout = nn.Dropout(dropout) def forward(self, text): #text = [sent len, batch size] text = text.permute(1, 0) #text = [batch size, sent len] embedded = self.embedding(text) #embedded = [batch size, sent len, emb dim] embedded = embedded.unsqueeze(1) #embedded = [batch size, 1, sent len, emb dim] conved = [F.relu(conv(embedded)).squeeze(3) for conv in self.convs] #conv_n = [batch size, n_filters, sent len - filter_sizes[n]] pooled = [F.max_pool1d(conv, conv.shape[2]).squeeze(2) for conv in conved] #pooled_n = [batch size, n_filters] cat = self.dropout(torch.cat(pooled, dim = 1)) #cat = [batch size, n_filters * len(filter_sizes)] return self.fc(cat) # 模型参数设置 INPUT_DIM = len(TEXT.vocab) EMBEDDING_DIM = 100 N_FILTERS = 100 FILTER_SIZES = [2,3,4] OUTPUT_DIM = len(LABEL.vocab) DROPOUT = 0.5 PAD_IDX = TEXT.vocab.stoi[TEXT.pad_token] model = CNN(INPUT_DIM, EMBEDDING_DIM, N_FILTERS, FILTER_SIZES, OUTPUT_DIM, DROPOUT, PAD_IDX) # 加载预训练模型 pretrained_embeddings = TEXT.vocab.vectors model.embedding.weight.data.copy_(pretrained_embeddings) # 用0初始化未知的权重和padding参数 UNK_IDX = TEXT.vocab.stoi[TEXT.unk_token] model.embedding.weight.data[UNK_IDX] = torch.zeros(EMBEDDING_DIM) model.embedding.weight.data[PAD_IDX] = torch.zeros(EMBEDDING_DIM) # 设置loss import torch.optim as optim optimizer = optim.Adam(model.parameters()) criterion = nn.CrossEntropyLoss() model = model.to(device) criterion = criterion.to(device) # 计算精确度 def categorical_accuracy(preds, y): """ Returns accuracy per batch, i.e. if you get 8/10 right, this returns 0.8, NOT 8 """ top_pred = preds.argmax(1, keepdim = True) correct = top_pred.eq(y.view_as(top_pred)).sum() acc = correct.float() / y.shape[0] return acc # 训练 def train(model, iterator, optimizer, criterion): epoch_loss = 0 epoch_acc = 0 model.train() for batch in iterator: optimizer.zero_grad() predictions = model(batch.text) loss = criterion(predictions, batch.label) acc = categorical_accuracy(predictions, batch.label) loss.backward() optimizer.step() epoch_loss += loss.item() epoch_acc += acc.item() return epoch_loss / len(iterator), epoch_acc / len(iterator) # 评价 def evaluate(model, iterator, criterion): epoch_loss = 0 epoch_acc = 0 model.eval() with torch.no_grad(): for batch in iterator: predictions = model(batch.text) loss = criterion(predictions, batch.label) acc = categorical_accuracy(predictions, batch.label) epoch_loss += loss.item() epoch_acc += acc.item() return epoch_loss / len(iterator), epoch_acc / len(iterator) # 时间统计 import time def epoch_time(start_time, end_time): elapsed_time = end_time - start_time elapsed_mins = int(elapsed_time / 60) elapsed_secs = int(elapsed_time - (elapsed_mins * 60)) return elapsed_mins, elapsed_secs # 训练模型 N_EPOCHS = 5 best_valid_loss = float('inf') for epoch in range(N_EPOCHS): start_time = time.time() train_loss, train_acc = train(model, train_iterator, optimizer, criterion) valid_loss, valid_acc = evaluate(model, valid_iterator, criterion) end_time = time.time() epoch_mins, epoch_secs = epoch_time(start_time, end_time) if valid_loss < best_valid_loss: best_valid_loss = valid_loss torch.save(model.state_dict(), 'tut5-model.pt') print(f'Epoch: {epoch+1:02} | Epoch Time: {epoch_mins}m {epoch_secs}s') print(f'\tTrain Loss: {train_loss:.3f} | Train Acc: {train_acc*100:.2f}%') print(f'\t Val. Loss: {valid_loss:.3f} | Val. Acc: {valid_acc*100:.2f}%') # 测试模型 model.load_state_dict(torch.load('tut5-model.pt')) test_loss, test_acc = evaluate(model, test_iterator, criterion) print(f'Test Loss: {test_loss:.3f} | Test Acc: {test_acc*100:.2f}%')
