·请参考本系列目录：【英文文本分类实战】之一——实战项目总览
·下载本实战项目资源：神经网络实现英文文本分类.zip（pytorch）
[1] 编写模型
1、TextRNN
参考论文《Recurrent Neural Network for Text Classification with Multi-Task Learning》提出的TextRNN模型，我们编写TextRNN模型，代码如下：
class Config(object): """配置参数""" def __init__(self, dataset, embedding): self.model_name = 'TextRNN' self.train_path = dataset + '/data/train.csv' # 训练集 self.dev_path = dataset + '/data/dev.csv' # 验证集 self.test_path = dataset + '/data/test.csv' # 测试集 self.class_list = [x.strip() for x in open( dataset + '/data/class.txt', encoding='utf-8').readlines()] # 类别名单 self.vocab_path = dataset + '/data/vocab.pkl' # 词表 self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt' # 模型训练结果 self.log_path = dataset + '/log/' + self.model_name self.embedding_pretrained = torch.tensor( np.load(dataset + '/data/' + embedding)["embeddings"].astype('float32'))\ if embedding != 'random' else None # 预训练词向量 self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # 设备 self.dropout = 0.5 # 随机失活 当num_layers=1,dropout是无用的 self.require_improvement = 1000 # 若超过1000batch效果还没提升，则提前结束训练 self.num_classes = len(self.class_list) # 类别数 self.n_vocab = 0 # 词表大小，在运行时赋值 self.num_epochs = 10 # epoch数 self.batch_size = 128 # mini-batch大小 self.pad_size = 14 # 每句话处理成的长度(短填长切) self.learning_rate = 1e-3 # 学习率 self.embed = self.embedding_pretrained.size(1)\ if self.embedding_pretrained is not None else 300 # 字向量维度, 若使用了预训练词向量，则维度统一 self.hidden_size = 128 # lstm隐藏层 self.num_layers = 2 # lstm层数 '''Recurrent Neural Network for Text Classification with Multi-Task Learning''' ''' shape : 1. embedding output shape : [batch_size, seq_len, embeding] = [128, 32, 300]. 2. lstm output shape : [batch_size, seq_len, hidden_size * 2] = [128, 32, 256] 此处的32不能再看成一句话内的32个词,已经变成了lstm的32个时刻. 3. out[:, -1, :] output shape : [batch_size, hidden_size * 2] = [128, 256] 取句子最后时刻的 hidden state. other: 1. lstm层数大小不会影响lstm的输出形状. 2. 双向lstm会使输出形状翻倍,即hidden_size * 2. ''' class Model(nn.Module): def __init__(self, config): super(Model, self).__init__() if config.embedding_pretrained is not None: self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False) else: self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1) self.lstm = nn.LSTM(config.embed, config.hidden_size, config.num_layers, bidirectional=True, batch_first=True, dropout=config.dropout) self.fc = nn.Linear(config.hidden_size * 2, config.num_classes) def forward(self, x): x, _ = x out = self.embedding(x) # [batch_size, seq_len, embeding] = [128, 32, 300] out, _ = self.lstm(out) # [batch_size, seq_len, hidden_size * 2]=[128, 32, 256] out = self.fc(out[:, -1, :]) # [batch_size, hidden_size * 2] = [128, 256] return out
2、DPCNN
参考论文《Deep Pyramid Convolutional Neural Networks for Text Categorization》提出的DPCNN模型，我们编写DPCNN模型，代码如下：
class Config(object): """配置参数""" def __init__(self, dataset, embedding): self.model_name = 'DPCNN' self.train_path = dataset + '/data/train.csv' # 训练集 self.dev_path = dataset + '/data/dev.csv' # 验证集 self.test_path = dataset + '/data/test.csv' # 测试集 self.class_list = [x.strip() for x in open( dataset + '/data/class.txt', encoding='utf-8').readlines()] # 类别名单 self.vocab_path = dataset + '/data/vocab.pkl' # 词表 self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt' # 模型训练结果 self.log_path = dataset + '/log/' + self.model_name self.embedding_pretrained = torch.tensor( np.load(dataset + '/data/' + embedding)["embeddings"].astype('float32'))\ if embedding != 'random' else None # 预训练词向量 self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # 设备 self.dropout = 0.5 # 随机失活 self.require_improvement = 1000 # 若超过1000batch效果还没提升，则提前结束训练 self.num_classes = len(self.class_list) # 类别数 self.n_vocab = 0 # 词表大小，在运行时赋值 self.num_epochs = 20 # epoch数 self.batch_size = 128 # mini-batch大小 self.pad_size = 14 # 每句话处理成的长度(短填长切) self.learning_rate = 1e-3 # 学习率 self.embed = self.embedding_pretrained.size(1)\ if self.embedding_pretrained is not None else 300 # 字向量维度 self.num_filters = 250 # 卷积核数量(channels数) '''Deep Pyramid Convolutional Neural Networks for Text Categorization''' class Model(nn.Module): def __init__(self, config): super(Model, self).__init__() if config.embedding_pretrained is not None: self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False) else: self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1) self.conv_region = nn.Conv2d(1, config.num_filters, (3, config.embed), stride=1) self.conv = nn.Conv2d(config.num_filters, config.num_filters, (3, 1), stride=1) self.max_pool = nn.MaxPool2d(kernel_size=(3, 1), stride=2) self.padding1 = nn.ZeroPad2d((0, 0, 1, 1)) # top bottom self.padding2 = nn.ZeroPad2d((0, 0, 0, 1)) # bottom self.relu = nn.ReLU() self.fc = nn.Linear(config.num_filters, config.num_classes) def forward(self, x): x = x[0] x = self.embedding(x) x = x.unsqueeze(1) # [batch_size, 250, seq_len, 1] # Region embedding 区域嵌入 3-gram x = self.conv_region(x) # [batch_size, 250, seq_len-3+1, 1] x = self.padding1(x) # [batch_size, 250, seq_len, 1] x = self.relu(x) x = self.conv(x) # [batch_size, 250, seq_len-3+1, 1] x = self.padding1(x) # [batch_size, 250, seq_len, 1] x = self.relu(x) x = self.conv(x) # [batch_size, 250, seq_len-3+1, 1] while x.size()[2] > 2: x = self._block(x) x = x.squeeze() # [batch_size, num_filters(250)] x = self.fc(x) return x def _block(self, x): x = self.padding2(x) px = self.max_pool(x) x = self.padding1(px) x = F.relu(x) x = self.conv(x) x = self.padding1(x) x = F.relu(x) x = self.conv(x) # Short Cut x = x + px return x
3、TextCNN
参考论文《Convolutional Neural Networks for Sentence Classification》提出的TextCNN模型，我们编写TextCNN模型，代码如下：
class Config(object): """配置参数""" def __init__(self, dataset, embedding): self.model_name = 'TextCNN' self.train_path = dataset + '/data/train.csv' # 训练集 self.dev_path = dataset + '/data/dev.csv' # 验证集 self.test_path = dataset + '/data/test.csv' # 测试集 self.class_list = [x.strip() for x in open( dataset + '/data/class.txt', encoding='utf-8').readlines()] # 类别名单 self.vocab_path = dataset + '/data/vocab.pkl' # 词表 self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt' # 模型训练结果 self.log_path = dataset + '/log/' + self.model_name self.embedding_pretrained = torch.tensor( np.load(dataset + '/data/' + embedding)["embeddings"].astype('float32'))\ if embedding != 'random' else None # 预训练词向量 self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # 设备 self.dropout = 0.5 # 随机失活 self.require_improvement = 1000 # 若超过1000batch效果还没提升，则提前结束训练 self.num_classes = len(self.class_list) # 类别数 self.n_vocab = 0 # 词表大小，在运行时赋值 self.num_epochs = 20 # epoch数 self.batch_size = 128 # mini-batch大小 self.pad_size = 14 # 每句话处理成的长度(短填长切) self.learning_rate = 1e-3 # 学习率 self.embed = self.embedding_pretrained.size(1)\ if self.embedding_pretrained is not None else 300 # 字向量维度 self.filter_sizes = (2, 3, 4) # 卷积核尺寸 self.num_filters = 256 # 卷积核数量(channels数) '''Convolutional Neural Networks for Sentence Classification''' class Model(nn.Module): def __init__(self, config): super(Model, self).__init__() if config.embedding_pretrained is not None: self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False) else: self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1) self.convs = nn.ModuleList( [nn.Conv2d(1, config.num_filters, (k, config.embed)) for k in config.filter_sizes]) self.dropout = nn.Dropout(config.dropout) self.fc = nn.Linear(config.num_filters * len(config.filter_sizes), config.num_classes) def conv_and_pool(self, x, conv): x = F.relu(conv(x)).squeeze(3) x = F.max_pool1d(x, x.size(2)).squeeze(2) return x def forward(self, x): out = self.embedding(x[0]) out = out.unsqueeze(1) out = torch.cat([self.conv_and_pool(out, conv) for conv in self.convs], 1) out = self.dropout(out) out = self.fc(out) return out
以上模型都是按照论文复现的，其中Config类的配置是几乎相同的，其中参数有：
·model_name：模型名称，在训练模型时，需要设置--model model_name；
·train_path、dev_path、test_path：训练集、验证集、测试集的地址；
·class_list：读取存放类别的txt文件，主要是为了获取有几个标签；
·vocab_path：词典地址；
·save_path：模型训练结果的存放地址；
·embedding_pretrained：读取预训练词向量，如果设置--embedding random那么不会读取预训练词向量，会随机生成词向量，在训练中反向更新；
·device：设备，选择使用GPU还是CPU；
·dropout：随机失活率，可以加在很多层上；
·require_improvement：若超过1000batch效果还没提升，则提前结束训练；
·num_classes：类别数；
·num_epochs：训练的epoch数；
·batch_size：一个batch中有几条文本；
·pad_size：每句话处理成的长度(短填长切)
·learning_rate：学习率。
[2] 模型训练-验证-测试代码
训练：
def train(config, model, train_iter, dev_iter, test_iter): start_time = time.time() model.train() optimizer = torch.optim.Adam(model.parameters(), lr=config.learning_rate) # 学习率指数衰减，每次epoch：学习率 = gamma * 学习率 # scheduler = torch.optim.lr_scheduler.ExponentialLR(optimizer, gamma=0.9) total_batch = 0 # 记录进行到多少batch dev_best_loss = float('inf') last_improve = 0 # 记录上次验证集loss下降的batch数 flag = False # 记录是否很久没有效果提升 writer = SummaryWriter(log_dir=config.log_path + '/' + time.strftime('%m-%d_%H.%M', time.localtime())) for epoch in range(config.num_epochs): print('Epoch [{}/{}]'.format(epoch + 1, config.num_epochs)) # scheduler.step() # 学习率衰减 for i, (trains, labels) in enumerate(train_iter): outputs = model(trains) model.zero_grad() loss = F.cross_entropy(outputs, labels) # print(f"&&&&&&&&&&{epoch}&&{i}") loss.backward() # print(f"###############{epoch}##{i}") optimizer.step() if total_batch % 100 == 0: # 每多少轮输出在训练集和验证集上的效果 true = labels.data.cpu() predic = torch.max(outputs.data, 1)[1].cpu() train_acc = metrics.accuracy_score(true, predic) dev_acc, dev_loss = evaluate(config, model, dev_iter) if dev_loss < dev_best_loss: dev_best_loss = dev_loss torch.save(model.state_dict(), config.save_path) improve = '*' last_improve = total_batch else: improve = '' time_dif = get_time_dif(start_time) msg = 'Iter: {0:>6}, Train Loss: {1:>5.2}, Train Acc: {2:>6.2%}, Val Loss: {3:>5.2}, Val Acc: {4:>6.2%}, Time: {5} {6}' print(msg.format(total_batch, loss.item(), train_acc, dev_loss, dev_acc, time_dif, improve)) writer.add_scalar("loss/train", loss.item(), total_batch) writer.add_scalar("loss/dev", dev_loss, total_batch) writer.add_scalar("acc/train", train_acc, total_batch) writer.add_scalar("acc/dev", dev_acc, total_batch) model.train() total_batch += 1 if total_batch - last_improve > config.require_improvement: # 验证集loss超过1000batch没下降，结束训练 print("No optimization for a long time, auto-stopping...") flag = True break if flag: break writer.close() test(config, model, test_iter)
评估：
def evaluate(config, model, data_iter, test=False): model.eval() loss_total = 0 predict_all = np.array([], dtype=int) labels_all = np.array([], dtype=int) with torch.no_grad(): for texts, labels in data_iter: outputs = model(texts) loss = F.cross_entropy(outputs, labels) loss_total += loss labels = labels.data.cpu().numpy() predic = torch.max(outputs.data, 1)[1].cpu().numpy() labels_all = np.append(labels_all, labels) predict_all = np.append(predict_all, predic) acc = metrics.accuracy_score(labels_all, predict_all) if test: report = metrics.classification_report(labels_all, predict_all, target_names=config.class_list, digits=4) confusion = metrics.confusion_matrix(labels_all, predict_all) return acc, loss_total / len(data_iter), report, confusion return acc, loss_total / len(data_iter)
评估：
def test(config, model, test_iter): # test model.load_state_dict(torch.load(config.save_path)) model.eval() start_time = time.time() test_acc, test_loss, test_report, test_confusion = evaluate(config, model, test_iter, test=True) msg = 'Test Loss: {0:>5.2}, Test Acc: {1:>6.2%}' print(msg.format(test_loss, test_acc)) print("Precision, Recall and F1-Score...") print(test_report) print("Confusion Matrix...") print(test_confusion) time_dif = get_time_dif(start_time) print("Time usage:", time_dif)
查看输出：每过100轮会打印一次
Epoch [1/10] Iter: 0, Train Loss: 2.1, Train Acc: 12.50%, Val Loss: 2.1, Val Acc: 15.15%, Time: 0:00:04 * Iter: 100, Train Loss: 0.9, Train Acc: 69.53%, Val Loss: 0.99, Val Acc: 65.16%, Time: 0:00:06 * Iter: 200, Train Loss: 0.9, Train Acc: 68.75%, Val Loss: 0.86, Val Acc: 70.27%, Time: 0:00:08 *
[3] 如何运行代码
模型主要有两个参数：
·model：模型名称；
·embedding：预训练词向量名称或者random。
在项目的run.py文件运行时同时添加参数，如下图：
