刘老师的《Pytorch深度学习实践》 第十三讲：循环神经网络（高级篇） 代码

import torch
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt
import torch.nn.functional as F
from torch.utils.data import Dataset, DataLoader
import torch.optim as optim
from torchvision import transforms
from torch.nn.utils.rnn import pack_padded_sequence
import time
import math
import csv
import gzip

HIDDEN_SIZE = 100
BATCH_SIZE = 256
N_LAYER = 2
N_EPOCHS = 100
N_CHAPS = 128
USE_GPU = False

class NameDataset(Dataset):
    def __init__(self,is_train_set = True):
        filename = 'names_train.csv.gz' if is_train_set else 'names_test.csv.gz'
        with gzip.open(filename,'rt') as f:
            reader = csv.reader(f)
            rows = list(reader)
        self.names = [row[0] for row in rows]
        self.len = len(self.names)
        self.countries = [row[1] for row in rows]
        self.country_list = list(sorted(set(self.countries))) #set去除重复
        self.country_dict = self.getCountryDict() #把列表转为词典
        self.country_num = len(self.country_list)

    def __getitem__(self,index): #名字是字符串，国家做索引
        return self.names[index],self.country_dict[self.countries[index]]

    def __len__(self):
        return self.len

    def getCountryDict(self):
        country_dict = dict()
        for idx,country_name in enumerate(self.country_list,0):
            country_dict[country_name] = idx
        return country_dict

    def getCountriesNum(self):
        return self.country_num

trainset = NameDataset(is_train_set = True)
trainloader = DataLoader(trainset,batch_size = BATCH_SIZE,shuffle = True)
testset = NameDataset(is_train_set = False)
testloader = DataLoader(testset,batch_size = BATCH_SIZE,shuffle = False)

N_COUNTRY = trainset.getCountriesNum()

def name2list(name):
    arr = [ord(c) for c in name]
    return arr, len(arr)

def create_tensor(tensor):
    if USE_GPU:
        device = torch.device("cuda:0")
        tensor = tensor.to(device)
    return tensor

class RNNClassifier(torch.nn.Module):
    def __init__(self,input_size,hidden_size,output_size,n_layers = 1,bidirectional = True):
        super(RNNClassifier,self).__init__()
        self.hidden_size = hidden_size
        self.n_layers = n_layers
        self.n_directions = 2 if bidirectional else 1

        self.embedding = torch.nn.Embedding(input_size,hidden_size)
        self.gru = torch.nn.GRU(hidden_size,hidden_size,n_layers,bidirectional = bidirectional)
        self.fc = torch.nn.Linear(hidden_size * self.n_directions,output_size)

    def _init_hidden(self,batch_size):
        hidden = torch.zeros(self.n_layers * self.n_directions,batch_size,self.hidden_size)
        return create_tensor(hidden)

    def forward(self,input,seq_lengths):
        input = input.t()
        batch_size = input.size(1)

        hidden = self._init_hidden(batch_size)
        embedding = self.embedding(input)

        gru_input = pack_padded_sequence(embedding,seq_lengths)

        output,hidden = self.gru(gru_input,hidden)
        if self.n_directions == 2:
            hidden_cat = torch.cat([hidden[-1],hidden[-2]],dim = 1)
        else:
            hidden_cat = hidden[-1]
        fc_output = self.fc(hidden_cat)
        return fc_output

def make_tensors(names,countries):
        sequences_and_lengths = [name2list(name) for name in names]
        name_sequences = [s1[0] for s1 in sequences_and_lengths]
        seq_lengths = torch.LongTensor([s1[1] for s1 in sequences_and_lengths])
        countries = countries.long()

        seq_tensor = torch.zeros(len(name_sequences),seq_lengths.max()).long()
        for idx,(seq,seq_len) in enumerate(zip(name_sequences,seq_lengths),0):
            seq_tensor[idx,:seq_len] = torch.LongTensor(seq)

        seq_lengths,perm_idx = seq_lengths.sort(dim = 0,descending = True)
        seq_tensor = seq_tensor[perm_idx]
        countries = countries[perm_idx]

        return create_tensor(seq_tensor),create_tensor(seq_lengths),create_tensor(countries)

def trainModel():
    total_loss = 0
    for i,(names,countries) in enumerate(trainloader,1):
        inputs,seq_lengths,target = make_tensors(names,countries)
        output = classifier(inputs,seq_lengths)
        loss = criterion(output,target)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_loss += loss.item()
        if i % 10 == 0:
            print(f'[{time_since(start)}] Epoch {epoch}',end = '')
            print(f'[{i * len(inputs)} / {len(trainset)}]',end = '')
            print(f'loss = {total_loss / (i * len(inputs))}')
    return total_loss

def testModel():
    correct = 0
    total = len(testset)
    print("evaluating trained model ...")
    with torch.no_grad():
        for i, (names,countries) in enumerate(testloader,1):
            inputs,seq_lengths,target = make_tensors(names,countries)
            output = classifier(inputs,seq_lengths)
            pred = output.max(dim =1,keepdim = True)[1]
            correct += pred.eq(target.view_as(pred)).sum().item()

        percent = '%.2f' % (100 * correct / total)
        print(f'Test set:Accuracy {correct} / {total} {percent} %')
    return correct / total

def time_since(since):
    s = time.time() - since
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m,s)

if __name__ == '__main__':
    classifier = RNNClassifier(N_CHAPS,HIDDEN_SIZE,N_COUNTRY,N_LAYER)
    if USE_GPU:
        device = torch.device("cuda:0")
        classifier.to(device)

    criterion = torch.nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(classifier.parameters(),lr = 0.001)

    start = time.time() #距离开始训练过去了多少时间
    print("Training for %d epochs..." % N_EPOCHS)
    acc_list = []
    for epoch in range(1,N_EPOCHS + 1):
        trainModel()
        acc = testModel()
        acc_list.append(acc) #测试的结果添加到列表中

    epoch = np.arange(1, len(acc_list) + 1, 1)
    acc_list = np.array(acc_list)
    plt.plot(epoch, acc_list)
    plt.xlabel('Epoch')
    plt.ylabel('Accuracy')
    plt.grid()
    plt.show()