Pytorch学习

下面将构造一个三层全连接层的神经网络来对手写数字进行识别。

数据集的载入

import torch
from torch import nn
from torch.nn import functional as F
from torch import optim

import torchvision
from matplotlib import pyplot as plt

batch_size=512
train_loader = torch.utils.data.DataLoader(
      torchvision.datasets.MNIST('mnist_data/',train=True, download=True,
                                transform=torchvision.transforms.Compose([
                                torchvision.transforms.ToTensor()])),
      batch_size=batch_size, shuffle=True)

test_loader = torch.utils.data.DataLoader(
    torchvision.datasets.MNIST('mnist_data/', train=False, download=True,
                               transform=torchvision.transforms.Compose([
                                   torchvision.transforms.ToTensor()])),
    batch_size=batch_size, shuffle=False)

数据集展示

def plot_image(img, label, name):

    fig = plt.figure()
    for i in range(6):
        plt.subplot(2, 3, i + 1)
        plt.tight_layout()
        plt.imshow(img[i][0], cmap='gray', interpolation='none')
        plt.title("{}: {}".format(name, label[i].item()))
        plt.xticks([])
        plt.yticks([])
    plt.show()
x, y = next(iter(train_loader))
print(x.shape, y.shape, x.min(), x.max())
plot_image(x, y, 'image sample')

输出图片如下：

网络搭建

#定义网络
class Net(nn.Module):
    
    def __init__(self):
        super(Net, self).__init__()
        
        #xw+b
        self.fc1 = nn.Linear(28*28,256)
        self.fc2 = nn.Linear(256,64)
        self.fc3 = nn.Linear(64,10)
        
    def forward(self,x):
        #x:[b,1,28,28]
        #h1 = relu(xw1+b1)
        x = F.relu(self.fc1(x))
        #h2 = relu(h1w2+b2)
        x = F.relu(self.fc2(x))
        #h3 = h2w3+b3
        x = self.fc3(x)
        
        return x

模型训练

net = Net()
# [w1, b1, w2, b2, w3, b3]
optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9)
criterion = nn.CrossEntropyLoss()

train_loss = []
for epoch in range(4):
    for batch_idx,(x,y) in enumerate(train_loader):
        
        #x:[b,1,28,28],y:[512]
        #[b,1,28,28]==>[b,784]
        x = x.view(x.size(0),28*28)
        #=>[b,10]
        out = net(x)
        loss = criterion(out,y)
        
        optimizer.zero_grad()
        loss.backward()
        
        #w'=w - lr*grad
        optimizer.step()
        
        train_loss.append(loss.item())
        
        if batch_idx %10 == 0:
            print(epoch,batch_idx,loss.item())

torch.nn.CrossEntropyLoss()使用注意
CrossEntropyLoss(将 nn.LogSoftmax() 和 nn.NLLLoss() 结合在一个类中)一般用于计算分类问题的损失值，可以计算出不同分布之间的差距。

训练损失函数图

def plot_curve(data):
    fig = plt.figure()
    plt.plot(range(len(data)), data, color='blue')
    plt.legend(['value'], loc='upper right')
    plt.xlabel('step')
    plt.ylabel('value')
    plt.show()

plot_curve(train_loss)

模型预测

#test
total_correct = 0
for x,y in test_loader:
    x = x.view(x.size(0),28*28)
    out = net(x)
    pred = out.argmax(dim=1)
    correct = pred.eq(y).sum().float().item()
    total_correct += correct
    
total_num = len(test_loader.dataset)
acc = total_correct/total_num
print("Teas ACC:",acc)