Pytorch-基础入门之RNN

RNN循环神经网络，也是一种很常见的神经网络了，在这里也不进行原理展示了。直接上代码。

这一块的话与上一篇逻辑斯蒂回归使用的是相同的数据集MNIST。

第一部分：构造模型

# Import Libraries
import torch
import torch.nn as nn
from torch.autograd import Variable

# Create RNN Model
class RNNModel(nn.Module):
    def __init__(self, input_dim, hidden_dim, layer_dim, output_dim):
        super(RNNModel, self).__init__()
        
        # Number of hidden dimensions
        self.hidden_dim = hidden_dim
        
        # Number of hidden layers
        self.layer_dim = layer_dim
        
        # RNN
        self.rnn = nn.RNN(input_dim, hidden_dim, layer_dim, batch_first=True, nonlinearity='relu')
        
        # Readout layer
        self.fc = nn.Linear(hidden_dim, output_dim)
    
    def forward(self, x):
        
        # Initialize hidden state with zeros
        h0 = Variable(torch.zeros(self.layer_dim, x.size(0), self.hidden_dim))
            
        # One time step
        out, hn = self.rnn(x, h0)
        out = self.fc(out[:, -1, :]) 
        return out

# batch_size, epoch and iteration
batch_size = 100
n_iters = 8000
num_epochs = n_iters / (len(features_train) / batch_size)
num_epochs = int(num_epochs)

# Pytorch train and test sets
train = TensorDataset(featuresTrain,targetsTrain)
test = TensorDataset(featuresTest,targetsTest)

# data loader
train_loader = DataLoader(train, batch_size = batch_size, shuffle = False)
test_loader = DataLoader(test, batch_size = batch_size, shuffle = False)
    
# Create RNN
input_dim = 28    # input dimension
hidden_dim = 100  # hidden layer dimension
layer_dim = 1     # number of hidden layers
output_dim = 10   # output dimension

model = RNNModel(input_dim, hidden_dim, layer_dim, output_dim)

# Cross Entropy Loss 
error = nn.CrossEntropyLoss()

# SGD Optimizer
learning_rate = 0.05
optimizer = torch.optim.SGD(model.p
arameters(), lr=learning_rate)

  第二部分：训练模型

seq_dim = 28  
loss_list = []
iteration_list = []
accuracy_list = []
count = 0
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):

        train  = Variable(images.view(-1, seq_dim, input_dim))
        labels = Variable(labels )
            
        # Clear gradients
        optimizer.zero_grad()
        
        # Forward propagation
        outputs = model(train)
        
        # Calculate softmax and ross entropy loss
        loss = error(outputs, labels)
        
        # Calculating gradients
        loss.backward()
        
        # Update parameters
        optimizer.step()
        
        count += 1
        
        if count % 250 == 0:
            # Calculate Accuracy         
            correct = 0
            total = 0
            # Iterate through test dataset
            for images, labels in test_loader:
                images = Variable(images.view(-1, seq_dim, input_dim))
                
                # Forward propagation
                outputs = model(images)
                
                # Get predictions from the maximum value
                predicted = torch.max(outputs.data, 1)[1]
                
                # Total number of labels
                total += labels.size(0)
                
                correct += (predicted == labels).sum()
            
            accuracy = 100 * correct / float(total)
            
            # store loss and iteration
            loss_list.append(loss.data)
            iteration_list.append(count)
            accuracy_list.append(accuracy)
            if count % 500 == 0:
                # Print Loss
                print('Iteration: {}  Loss: {}  Accuracy: {} %'.format(count, loss.data[0], accuracy))

 结果：

Iteration: 500  Loss: 1.4726558923721313  Accuracy: 42.726190476190474 %
Iteration: 1000  Loss: 0.7108388543128967  Accuracy: 71.73809523809524 %
Iteration: 1500  Loss: 0.43755194544792175  Accuracy: 85.22619047619048 %
Iteration: 2000  Loss: 0.271086722612381  Accuracy: 90.25 %
Iteration: 2500  Loss: 0.2235582023859024  Accuracy: 89.5 %
Iteration: 3000  Loss: 0.09727417677640915  Accuracy: 92.66666666666667 %
Iteration: 3500  Loss: 0.42934906482696533  Accuracy: 92.6547619047619 %
Iteration: 4000  Loss: 0.09869173169136047  Accuracy: 94.19047619047619 %
Iteration: 4500  Loss: 0.2372802197933197  Accuracy: 95.20238095238095 %
Iteration: 5000  Loss: 0.10717732459306717  Accuracy: 95.19047619047619 %
Iteration: 5500  Loss: 0.23859672248363495  Accuracy: 94.69047619047619 %
Iteration: 6000  Loss: 0.15453924238681793  Accuracy: 96.05952380952381 %
Iteration: 6500  Loss: 0.07914035022258759  Accuracy: 95.97619047619048 %
Iteration: 7000  Loss: 0.12296199798583984  Accuracy: 96.27380952380952 %
Iteration: 7500  Loss: 0.10664860904216766  Accuracy: 96.11904761904762 %

 第三部分：可视化展示