NLP（七）：textCNN

一、代码

import torch.optim as optim
import torch.utils.data as Data
import torch.nn.functional as F
from model.word_2_vector import WordEmbedding
import os
import pandas as pd
from pre_process.dataset_iter import DatasetIter

class TextCNN(nn.Module):
    def __init__(self):
        super(TextCNN, self).__init__()
        output_channel = 3
        self.conv1 = nn.Sequential(
            # conv : [input_channel(=1), output_channel, (filter_height, filter_width), stride=1]
            nn.Conv2d(1, output_channel, (10, 128)),
            nn.ReLU(),
            nn.MaxPool2d((5, 1))
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(3, 6, (5, 1)),
            nn.ReLU(),
            nn.MaxPool2d((4,1))
        )
        self.conv3 = nn.Sequential(
            nn.Conv2d(6, 3, (10, 1)),
            nn.ReLU(),
            nn.MaxPool2d((4,1))
        )
        # pool : ((filter_height, filter_width))
        self.fc = nn.Sequential(
            nn.Linear(66, 4),

        )


    def forward(self, X):
      '''
      X: [batch_size, sequence_length]
      '''
      batch_size = X.shape[0]
      embedding_X = X # [batch_size, sequence_length, embedding_size]
      embedding_X = embedding_X.unsqueeze(1) # add channel(=1) [batch, channel(=1), sequence_length, embedding_size]
      conved = self.conv1(embedding_X) # [batch_size, output_channel*1*1]
      conve2 = self.conv2(conved)
      conve3 = self.conv3(conve2)
      flatten = conve3.view(batch_size, -1)
      output = self.fc(flatten)
      return output

def binary_acc(preds, y):
    pred = torch.argmax(preds, dim=1)
    correct = torch.eq(pred, y).float()
    acc = correct.sum() / len(correct)
    return acc

def run_text_cnn():
    parent_path = os.path.split(os.path.realpath(__file__))[0]
    root = parent_path[:parent_path.find("model")]
    BATCH_SIZE = 16
    _path = os.path.join(root, "datas", "annotate", "labeled.csv")
    data_frame = pd.read_csv(_path, sep="\t")
    label = data_frame["labels"]
    sentences = data_frame["datas"]
    word = WordEmbedding()
    dataset = DatasetIter(sentences, label)
    loader = Data.DataLoader(dataset, BATCH_SIZE, True)
    model = TextCNN()
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.Adam(model.parameters(), lr=1e-3)
    for epoch in range(1000):
        avg_acc = []
        avg_loss = []
        model.train()
        for batch_x, batch_y in loader:
            x = word.sentenceTupleToEmbedding(batch_x)
            pred = model(x)
            loss = criterion(pred, batch_y)
            acc = binary_acc(pred, batch_y)
            avg_acc.append(acc)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            avg_loss.append(loss.item())
        avg_acc = np.array(avg_acc).mean()
        avg_loss = np.array(avg_loss).mean()
        print('train acc:', avg_acc)
        print("train loss", avg_loss)

 

 二、图形