利用pytorch 实现循环神经网络(RNN)

循环神经网络

这里有一篇英文文章说的比较好，这里我直接拿来用了，同时也可以帮大家提升一下英文水平，哈哈哈


原文

代码实现

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

#device configuration
device=torch.device('cuda'if torch.cuda.is_available()else 'cpu')

#hyper-parameters
sequence_length=28
input_size=28
hidden_size=128
num_classes=10
num_layers=2
batch_size=100

num_epochs=5
learning_rate=0.01

#MNIST dataset
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())

#data loader
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)

#recurrent neural network(many to one)
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
model=RNN(input_size,hidden_size,num_layers,num_classes).to(device)
#loss and optimizer
criterion=nn.CrossEntropyLoss()
optimizer=torch.optim.Adam(model.parameters(),lr=learning_rate)

#train the model
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)

        #forward pass
        outputs=model(images)
        loss=criterion(outputs,labels)
        #backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if(i+1)%100==0:
            print('epoch[{}/{}],step[{}/{}],loss:{:.4f}'.format(epoch+1,num_epochs,i+1,total__step,loss.item()))
#test the model
model.eval()
with torch.no_grad():
    correct=0
    total=0
    for images,labels in test_loader:
        images=images.reshape(-1,sequence_length,input_size).to(device) #resize images to satisfy the model requirement
        labels=labels.to(device)
        outputs=model(images)
        _,predicted=torch.max(outputs.data,1)
        total+=labels.size(0)
        correct+=(predicted==labels).sum().item()
    print('test accuarcy of the model on the 10000 test images:{}%'.format(100*correct/total))
#save the model checkpoint
torch.save(model.state_dict(),'model.ckpt_4')

输出结果