0
点赞
收藏
分享

微信扫一扫

B站 刘二大人 深度学习 pytorch 第十三讲代码

勇敢的趙迦禾 2022-04-27 阅读 61
python深度学习pytorch

用RNN实现 输入name 系统识别country （CPU版本 因此GPU的一些语句省略了~）

1.导入所需包

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

2.参数设置

####参数设置
HIDDEN_SIZE = 100
BATCH_SIZE = 256
N_LAYER = 2
N_EPOCHS = 100
N_CHARS = 128  ####输入字典长度
USE_GPU = False

3.NameDataset类

class NameDataset(Dataset):
    def __init__(self, is_train_set=True):
        filename = 'C:/Users/xxx/Desktop/pytorchliuer/names_train.csv.gz' if is_train_set else 'C:/Users/xxx/Desktop/pytorchliuer/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)))
        self.country_dict = self.getCountryDict()
        self.country_num = len(self.country_list)

    def __getitem__(self, index):
        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 idx2country(self,index):
        return self.country_list[index]

    def getCountriesNum(self):
        return self.country_num

4.数据准备工作

####数据准备工作
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()

5.网络模型

#####模型设计
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 = 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 = hidden[-1]
        fc_output = self.fc(hidden_cat)
        return fc_output

6.功能函数构建

def make_tensors(names,countries):
    sequences_and_lengths = [name2list(name) for name in names]
    name_sequences = [sl[0] for sl in sequences_and_lengths]
    seq_lengths = torch.LongTensor([sl[1] for sl 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 name2list(name):
    arr = [ord(c) for c in name]
    return arr,len(arr)


def create_tensor(tensor):
    return tensor


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

7.训练

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

8.测试

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

9.函数入口

if __name__ == '__main__':
    classifier = RNNClassifier(N_CHARS,HIDDEN_SIZE,N_COUNTRY,N_LAYER)
    
    criterion = torch.nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(classifier.parameters(),lr = 0.001)
    
    start = time.time()
    print("Training for %d epochs..." % N_EPOCHS)
    acc_list = []
    for epoch in range(1,N_EPOCHS+1):
        trainModel()
        acc = testModel()
        acc_list.append(acc)

完整代码：

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

####参数设置
HIDDEN_SIZE = 100
BATCH_SIZE = 256
N_LAYER = 2
N_EPOCHS = 100
N_CHARS = 128  ####输入字典长度
USE_GPU = False

class NameDataset(Dataset):
    def __init__(self, is_train_set=True):
        filename = 'C:/Users/xxx/Desktop/pytorchliuer/names_train.csv.gz' if is_train_set else 'C:/Users/xxx/Desktop/pytorchliuer/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)))
        self.country_dict = self.getCountryDict()
        self.country_num = len(self.country_list)

    def __getitem__(self, index):
        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 idx2country(self,index):
        return self.country_list[index]

    def getCountriesNum(self):
        return self.country_num

####数据准备工作
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()

#####模型设计
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 = 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 = 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 = [sl[0] for sl in sequences_and_lengths]
    seq_lengths = torch.LongTensor([sl[1] for sl 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 name2list(name):
    arr = [ord(c) for c in name]
    return arr,len(arr)

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

def create_tensor(tensor):
    return tensor

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

if __name__ == '__main__':
    classifier = RNNClassifier(N_CHARS,HIDDEN_SIZE,N_COUNTRY,N_LAYER)
    
    criterion = torch.nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(classifier.parameters(),lr = 0.001)
    
    start = time.time()
    print("Training for %d epochs..." % N_EPOCHS)
    acc_list = []
    for epoch in range(1,N_EPOCHS+1):
        trainModel()
        acc = testModel()
        acc_list.append(acc)

输出：训练了20个epoch：

 

 

 

举报

相关推荐

刘二大人《pytorch深度学习》 第三讲 梯度下降算法

pytorch深度学习算法

刘二大人《Pytorch深度学习实践》02.线性模型

pytorch深度学习python

【Pytorch深度学习开发实践学习】B站刘二大人课程笔记整理lecture09 Softmax多分类

深度学习pytorch学习

刘二大人《Pytorch深度学习与实践》09多分类问题作业，

pytorch深度学习分类

Pytorch深度学习实践（b站刘二大人）P10讲 (CNN卷积神经网络高级篇 作业)

pytorch深度学习cnn

【Pytorch深度学习开发实践学习】B站刘二大人课程笔记整理lecture11 Advanced_CNN 实现GoogleNet和ResNet

算法科技素养

河北工业大学刘二大人

深度学习机器学习python

刘二大人 PyTorch深度学习实践 笔记 P11 卷积神经网络（高级篇）

深度学习cnnpytorch

unidbg第十三讲 unidbg实战

javafridaunidbghook逆向

第十三讲：属性&析构函数

c#
0 条评论