前言
任务是这样的,我们需要设计一个模型,针对不同的名字,判断他到底是哪个国家。
比如:
bob 英国的
bingbing Wang 中国的
一、先上代码
#根据名字分类国家
import numpy as np
import torch
from torch.utils.data import DataLoader,Dataset
import matplotlib.pyplot as plt
import gzip
import csv
import time
class NameDataset(Dataset):
def __init__(self,is_train_set=True):
filename='names_train.csv.gz'if is_train_set else'names_test.csv.gz'
#多种不同的方式读取数据,gzip格式如下
with gzip.open(filename,'rt') as f:
reader=csv.reader(f)
rows=list(reader)#name,lauguage对
self.names=[row[0] for row in rows]
self.len=len(self.names)
self.countries=[row[1] for row in rows]
#set 集合,去除重复元素 sort排序 list变成列表
self.country_list=list(sorted(set(self.countries)))
#country变成一个字典
self.country_dict=self.getCountryDict()
self.country_num=len(self.country_list)#索引总数
#save countries and its index in list and dictionary
def __getitem__(self, index):
#名字string country索引
return self.names[index],self.country_dict[self.countries[index]]
def __len__(self):
return self.len
#convert list to dictionary
def getCountryDict(self):
country_dict=dict()#空字典
for idx,country_name in enumerate(self.country_list,0):
country_dict[country_name]=idx
return country_dict
#表示方便
def idx2country(self,index):
return self.country_list[index]
def getCountriesNum(self):
return self.country_num
class RNNclassifier(torch.nn.Module):
def __init__(self,input_size,hidden_size,output_size,n_layers=1,bidirectional=True):
super(RNNclassifier,self).__init__()
#GRN layer 参数
self.hidden_size=hidden_size
self.n_layers=n_layers
self.n_directions=2 if bidirectional else 1
#(seqlen,batchsize)(seqlen,batchsize,hiddensize)
#嵌入字典的大小,每个嵌入向量的大小
self.embed=torch.nn.Embedding(input_size,hidden_size)#嵌入向量维度=隐藏层维度
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)
#创建全0隐藏
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 shape B X S ->S X B
input=input.t()#embedding 需要的维度
batch_size=input.size(1)
hidden=self._init_hidden(batch_size)
embedding=self.embed(input)
#pack them up简化gru计算,输入的未emb的数据必须根据序列长度排序,把0去掉
gru_input=torch.nn.utils.rnn.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=torch.cat(hidden[-1])
#最后的隐层输出hN
fc_output=self.fc(hidden_cat)
return fc_output
def name2list(name):
arr= [ord(c) for c in name]
return arr,len(arr)
# name to tensor
def make_tensors(names,countries):
#name分字符ASCLL,返回arr,len(arr)
sequences_and_lengths=[name2list(name) for name in names]
#分开拿出来
#ascll姓名列表
name_sequences=[sl[0] for sl in sequences_and_lengths]
#长度列表
seq_lengths=torch.LongTensor([sl[1] for sl in sequences_and_lengths])
#countries转化为long
countries=countries.long()
#make tensor of name B x S padding填充
seq_tensor=torch.zeros(len(name_sequences),seq_lengths.max()).long()#bug1
#转化为长整形long(),才可以被embed接受
for idx,(seq,seq_len) in enumerate(zip(name_sequences,seq_lengths)):
seq_tensor[idx,:seq_len]=torch.LongTensor(seq)
#sort by length to use pack_padded_sequence排序
seq_lengths,perm_idx=seq_lengths.sort(dim=0,descending=True)
#排序的索引
seq_tensor=seq_tensor[perm_idx]
countries=countries[perm_idx]
return create_tensor(seq_tensor),\
create_tensor(seq_lengths),\
create_tensor(countries)
def create_tensor(tensor):
if USE_GPU:
device=torch.device("cude:0")
tensor=tensor.to(device)
return tensor
def trainModel():
total_loss=0
for i,(names,countries) in enumerate(trainloader,1):
inputs,seq_lengths,target=make_tensors(names,countries)
outputs=classifier(inputs,seq_lengths)
loss=criterion(outputs,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_len,target=make_tensors(names,countries)
output=classifier(inputs,seq_len)
pred=output.max(dim=1,keepdim=True)[1]
correct+=pred.eq(target.view_as(pred)).sum().item()
precent='%.2f'%(100*correct/total)
print(f'test set:accuracy {correct}/{total} {precent}%')
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__':
# parameter
HIDDEN_SIZE = 100 # 隐藏层维度
BATCH_SIZE = 256 # batch大小
N_LAYER = 2 # gru维度
N_EOPCHS = 30 # 循环次数
N_CHARS = 128 # 字典大小,ASLL码表示
USE_GPU = False # 不用GPU
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() # 输出的维度
classifier=RNNclassifier(N_CHARS,HIDDEN_SIZE,N_COUNTRY,N_LAYER)
if USE_GPU:
device = torch.device("cude:0")
classifier.to(device)
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(classifier.parameters(), lr=0.01)
start=time.time()
print("training for %d epochs..."%N_EOPCHS)
acc_list=[]
for epoch in range(1,N_EOPCHS+1):
print('epoch',epoch)
trainModel()
acc=testModel()
acc_list.append(acc)
#画图
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()
。