import math
import time
import torch
import matplotlib.pyplot as plt
import numpy as np
import gzip
import csv
from torch.nn.utils.rnn import pack_padded_sequence
from torch.utils.data import Dataset, DataLoader
#1.构建数据集
HIDDEN_SIZE = 100
BATCH_SIZE = 256
N_LAYER = 2
N_EPOCHS = 100
N_CHARS = 128 # 字典长度
USE_GPU = False
class NameDataset(Dataset):
def __init__(self, is_train_set=True):
filename = 'D:\迅雷下载/names_train.csv.gz' if is_train_set else 'D:\迅雷下载/names_test.csv.gz'
with gzip.open(filename, 'rt') as f:
reader = csv.reader(f)
rows = list(reader) #(name,language)
self.names = [row[0] for row in rows] #(name,language) 的第零维,接入到其中去
self.len = len(self.names)
self.countries = [row[1] for row in rows]
self.country_list = list(sorted(set(self.countries))) #set 构建集合 去掉重复的国家 sort 排序 list 构建列表
self.country_dict = self.getCountryDict() #将列表转化为词典
self.country_num = len(self.country_list)
def __getitem__(self, index):#索引 通过下标返回name 通过下标找到name对应得language 然后根据词典返回对应language得数字
return self.names[index], self.country_dict[self.countries[index]]
def __len__(self):
return self.len
def getCountryDict(self):
country_dict = dict()#构建空字典
for idx, country_name in enumerate(self.country_list, 0):#对产生上一个类产生得排序后得列表进行遍历
country_dict[country_name] = idx#构建字典
return country_dict
def idx2country(self, index):#根据索引,返回国家
return self.country_list[index]
def getCountriesNum(self):#读出国家数
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() #决定最终输出维度得大小
#2.搭建神经网络
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) #(seqlen,batchsize)->(seqlen,batchsize,hiddensize)
self.gru = torch.nn.GRU(hidden_size, hidden_size, n_layers, #第二个是输出维度 input(seqlen,batchsize,hiddensize)->(seqlen,batchsize,hiddensize*nDirections)
bidirectional=bidirectional) #说明单向 1 or双向 2 hidden(nlayers*nDirections,batchsize,hiddensize) 维度不变
self.fc = torch.nn.Linear(hidden_size * self.n_directions, output_size)#hiddensize*2是因为两次拼接
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() # 转置 t -> transpose: input shape : B x S -> S x B
batch_size = input.size(1)
hidden = self._init_hidden(batch_size) # h0(nLayer*nDirection,batchsize,hiddensize)
embedding = self.embedding(input) # out=(seqLen,batchSize,hiddenSize)
# PackedSquence:把为0的填充量去除,把每个样本的长度记录下来,按长度排序(长度是降序)后拼接在一起 先长度排序后 经过嵌入层embed
gru_input = pack_padded_sequence(embedding, seq_lengths)
output, hidden = self.gru(gru_input, hidden) #hidden(nlayers*nDirections,batchsize,hiddensize)
if self.n_directions == 2: # 双向循环神经网络有两个hidden
hidden_cat = torch.cat([hidden[-1], hidden[-2]], dim=1) #在batchsize维度进行拼接
else:
hidden_cat = hidden[-1]
fc_output = self.fc(hidden_cat)
return fc_output
classifier = RNNClassifier(N_CHARS, HIDDEN_SIZE, N_COUNTRY, N_LAYER)
#3.定义优化器和损失函数
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(classifier.parameters(), lr=0.001)
#本模块对name进行处理
def name2list(name): #name to list
arr = [ord(c) for c in name] # 返回对应字符的 ASCII 数值 将name 转化为对应各个字符ASCII得列表
return arr, len(arr) # 返回元组,列表本身和列表长度
def make_tensors(names, countries):
sequences_and_lengths = [name2list(name) for name in names]
name_sequences = [sl[0] for sl in sequences_and_lengths] #所有name得ASCII得列表组成得列表
seq_lengths = torch.LongTensor([sl[1] for sl in sequences_and_lengths]) #所有name得ASCII得列表得长度组成得列表
countries = countries.long() # countries:国家索引 整两个整数都转化成LongTensor
# make tensor of name, BatchSize x SeqLen (做padding,先做一个全零得张量,然后将非零量粘贴过去)
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)
# 排序(按照序列长度),sort by length to use pack_padded_sequence
seq_lengths, perm_idx = seq_lengths.sort(dim=0, descending=True)#返回序列长度得列表以及对应序列长度得索引
# sort返回两个值,seq_lengths:排完序后的序列(未padding),perm_idx:排完序后对应元素的索引
seq_tensor = seq_tensor[perm_idx] # 排序(已padding)
countries = countries[perm_idx] # 排序(标签)
return create_tensor(seq_tensor), create_tensor(seq_lengths), create_tensor(countries)
def time_since(since):
s = time.time() - since
m = math.floor(s / 60)
s -= m * 60
return '%dm %ds' % (m, s)
def trainModel():
total_loss = 0
for i, (names, countries) in enumerate(trainloader, 1):
inputs, seq_lengths, target = make_tensors(names, countries) # make_tensors
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) # make_tensors
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
if __name__ == '__main__':
classifier = RNNClassifier(N_CHARS, HIDDEN_SIZE, N_COUNTRY, N_LAYER) #构造分类器:派生类 解决名字字符长度的不同
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() #返回的是s为单位的时间
print("Training for %d epochs..." % N_EPOCHS)
acc_list = []
for epoch in range(1, N_EPOCHS + 1):
# Train cycle
trainModel()
acc = testModel()
acc_list.append(acc) #将准确率记录到列表里
# 绘图
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()
循环神经网络:姓名国别分类实操
猜你喜欢
转载自blog.csdn.net/qq_21686871/article/details/115433416
今日推荐
周排行