MachineLP的部落格目錄：小鵬的部落格目錄

本小節使用torch搭建RNN模型，訓練和測試：

（1）定義模型超引數：rnn的輸入，rnn隱含單元，rnn層數，迭代次數、批量大小、學習率。

（3）定義模型（定義需要的RNN結構）。

（4）定義損失函式，選用適合的損失函式。

（5）定義優化演算法（SGD、Adam等）。

（6）儲存模型。

---------------------------------我是可愛的分割線---------------------------------

程式碼部分：

# coding=utf-8

import torch 
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms


# 判定GPU是否存在 
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# 定義超引數
# RNN的輸入是一個序列，sequence_length為序列長度，input_size為序列每個長度。
sequence_length = 28
input_size = 28
# 定義RNN隱含單元的大小。
hidden_size = 128
# 定義rnn的層數
num_layers = 2
# 識別的類別數量
num_classes = 10
# 批的大小
batch_size = 100
# 定義迭代次數
num_epochs = 2
# 定義學習率
learning_rate = 0.01

# MNIST 資料集  
train_dataset = torchvision.datasets.MNIST(root='./data/',
                                           train=True, 
                                           transform=transforms.ToTensor(),
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='./data/',
                                          train=False, 
                                          transform=transforms.ToTensor())

# 構建資料管道， 使用自己的資料集請參考：https://blog.csdn.net/u014365862/article/details/80506147 
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size, 
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size, 
                                          shuffle=False)

# 定義RNN（LSTM）
class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(RNN, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size, num_classes)
    
    def forward(self, x):
        # Set initial hidden and cell states 
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device) 
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
        
        # Forward propagate LSTM
        out, _ = self.lstm(x, (h0, c0))  # out: tensor of shape (batch_size, seq_length, hidden_size)
        
        # Decode the hidden state of the last time step
        out = self.fc(out[:, -1, :])
        return out

# 定義模型 
model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)


# 損失函式和優化演算法
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# 訓練模型 
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)
        
        # 前向傳播+計算loss  
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # 後向傳播+調整引數 
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        # 每100個batch列印一次資料    
        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# 模型測試部分    
# 測試階段不需要計算梯度，注意  
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total)) 

# 儲存模型引數   
torch.save(model.state_dict(), 'model.ckpt')
 

加餐1：在自己資料集上使用：

其中，train.txt中的資料格式：

gender/0male/0(2).jpg 1
gender/0male/0(3).jpeg 1
gender/0male/0(1).jpg 0

test.txt中的資料格式如下：

gender/0male/0(3).jpeg 1
gender/0male/0(1).jpg 0

gender/1female/1(6).jpg 1

程式碼部分：

# coding=utf-8
import torch     
import torch.nn as nn    
import torchvision    
from torch.utils.data import Dataset, DataLoader        
from torchvision import transforms, utils     
from PIL import Image  


# 判定GPU是否存在 
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# 定義超引數
# RNN的輸入是一個序列，sequence_length為序列長度，input_size為序列每個長度。
sequence_length = 28*3
input_size = 28
# 定義RNN隱含單元的大小。
hidden_size = 128
# 定義rnn的層數
num_layers = 2
# 識別的類別數量
num_classes = 10
# 批的大小
batch_size = 16
# 定義迭代次數
num_epochs = 2
# 定義學習率
learning_rate = 0.01

def default_loader(path):        
    # 注意要保證每個batch的tensor大小時候一樣的。        
    return Image.open(path).convert('RGB')        
        
class MyDataset(Dataset):        
    def __init__(self, txt, transform=None, target_transform=None, loader=default_loader):        
        fh = open(txt, 'r')        
        imgs = []        
        for line in fh:        
            line = line.strip('\n')        
            # line = line.rstrip()        
            words = line.split(' ')        
            imgs.append((words[0],int(words[1])))        
        self.imgs = imgs        
        self.transform = transform        
        self.target_transform = target_transform        
        self.loader = loader        
            
    def __getitem__(self, index):        
        fn, label = self.imgs[index]        
        img = self.loader(fn)        
        if self.transform is not None:        
            img = self.transform(img)        
        return img,label        
            
    def __len__(self):        
        return len(self.imgs)        
        
def get_loader(dataset='train.txt', crop_size=128, image_size=28, batch_size=2, mode='train', num_workers=1):        
    """Build and return a data loader."""        
    transform = []        
    if mode == 'train':        
        transform.append(transforms.RandomHorizontalFlip())        
    transform.append(transforms.CenterCrop(crop_size))        
    transform.append(transforms.Resize(image_size))        
    transform.append(transforms.ToTensor())        
    transform.append(transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)))        
    transform = transforms.Compose(transform)        
    train_data=MyDataset(txt=dataset, transform=transform)        
    data_loader = DataLoader(dataset=train_data,        
                                  batch_size=batch_size,        
                                  shuffle=(mode=='train'),        
                                  num_workers=num_workers)        
    return data_loader        
# 注意要保證每個batch的tensor大小時候一樣的。        
# data_loader = DataLoader(train_data, batch_size=2,shuffle=True)        
train_loader = get_loader('train.txt', batch_size=batch_size)        
print(len(train_loader))        
test_loader = get_loader('test.txt', batch_size=batch_size)        
print(len(test_loader))    

# 定義RNN（LSTM）
class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(RNN, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size, num_classes)
    
    def forward(self, x):
        # Set initial hidden and cell states 
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device) 
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
        
        # Forward propagate LSTM
        out, _ = self.lstm(x, (h0, c0))  # out: tensor of shape (batch_size, seq_length, hidden_size)
        
        # Decode the hidden state of the last time step
        out = self.fc(out[:, -1, :])
        return out

# 定義模型 
model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)


# 損失函式和優化演算法
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# 訓練模型 
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)
        
        # 前向傳播+計算loss  
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # 後向傳播+調整引數 
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        # 每100個batch列印一次資料    
        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# 模型測試部分    
# 測試階段不需要計算梯度，注意  
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total)) 

# 儲存模型引數   
torch.save(model.state_dict(), 'model.ckpt')
 

加餐2：BIRNN

# coding=utf-8
import torch 
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms


# 判定GPU是否存在 
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# 定義超引數  
# RNN的輸入是一個序列，sequence_length為序列長度，input_size為序列每個長度。
sequence_length = 28
input_size = 28
# 定義RNN隱含單元的大小。 
hidden_size = 128
# 定義rnn的層數
num_layers = 2
num_classes = 10
batch_size = 100
num_epochs = 2
learning_rate = 0.003

# MNIST 資料集
train_dataset = torchvision.datasets.MNIST(root='./data/',
                                           train=True, 
                                           transform=transforms.ToTensor(),
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='./data/',
                                          train=False, 
                                          transform=transforms.ToTensor())

# 構建資料管道， 使用自己的資料集請參考：https://blog.csdn.net/u014365862/article/details/80506147  
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size, 
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size, 
                                          shuffle=False)

# 定義RNN（LSTM） 
class BiRNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(BiRNN, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True, bidirectional=True)
        self.fc = nn.Linear(hidden_size*2, num_classes)  # 2 for bidirection
    
    def forward(self, x):
        # Set initial states
        h0 = torch.zeros(self.num_layers*2, x.size(0), self.hidden_size).to(device) # 2 for bidirection 
        c0 = torch.zeros(self.num_layers*2, x.size(0), self.hidden_size).to(device)
        
        # Forward propagate LSTM
        out, _ = self.lstm(x, (h0, c0))  # out: tensor of shape (batch_size, seq_length, hidden_size*2)
        
        # Decode the hidden state of the last time step
        out = self.fc(out[:, -1, :])
        return out

# 定義模型
model = BiRNN(input_size, hidden_size, num_layers, num_classes).to(device)

# 損失函式和優化演算法 
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
    
# 訓練模型 
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)
        
        # 前向傳播+計算loss    
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # 後向傳播+調整引數   
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        # 每100個batch列印一次資料      
        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# 模型測試部分      
# 測試階段不需要計算梯度，注意 
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total)) 

# 儲存模型引數
torch.save(model.state_dict(), 'model.ckpt')
 

---------------------------------我是可愛的分割線---------------------------------

總結：

本節使用RNN訓練MNIST識別、自己資料的識別。

torch系列：