Pytorch基本练习-Fashion

数据准备：

import torch
from torchvision import datasets, transforms

# Define a transform to normalize the data
transform = transforms.Compose([transforms.ToTensor(),
                                transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# Download and load the training data
trainset = datasets.FashionMNIST('~/.pytorch/F_MNIST_data/', download=True, train=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)

# Download and load the test data
testset = datasets.FashionMNIST('~/.pytorch/F_MNIST_data/', download=True, train=False, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=True)

Pytorch构建BP神经网络

class Classifier(nn.Module):
    def __init__(self):
        super().__init__()        
        self.fc1 = nn.Linear(784, 256)
        self.fc2 = nn.Linear(256, 128)
        self.fc3 = nn.Linear(128, 64)
        self.fc4 = nn.Linear(64, 10)

        # Dropout module with 0.2 drop probability
        self.dropout = nn.Dropout(p=0.2)

    def forward(self, x):
        # make sure input tensor is flattened
        x = x.view(x.shape[0], -1)    #修改输入x的size

        # Now with dropout
        x = self.dropout(F.relu(self.fc1(x)))
        x = self.dropout(F.relu(self.fc2(x)))
        x = self.dropout(F.relu(self.fc3(x)))

        # output so no dropout here
        x = F.log_softmax(self.fc4(x), dim=1)

        return x

BP神经网络训练

model = Classifier()    
criterion = nn.NLLLoss()        #损失函数
optimizer = optim.Adam(model.parameters(), lr=0.003)        #优化器

epochs = 30
steps = 0

train_losses, test_losses = [], []
for e in range(epochs):
    running_loss = 0
    for images, labels in trainloader:
        
        optimizer.zero_grad()        #损失梯度清0
        
        log_ps = model(images)        #模型输入，获得输出
        loss = criterion(log_ps, labels)    #获得损失误差
        loss.backward()        #反向传播
        optimizer.step()        #更新权重
        
        running_loss += loss.item()    #误差累加
        
    else:
        test_loss = 0
        accuracy = 0
        
        # Turn off gradients for validation, saves memory and computations
        with torch.no_grad():     #梯度不回传
            model.eval()        
            for images, labels in testloader:
                log_ps = model(images)
                test_loss += criterion(log_ps, labels)
                
                ps = torch.exp(log_ps)
                top_p, top_class = ps.topk(1, dim=1)
                equals = top_class == labels.view(*top_class.shape)
                accuracy += torch.mean(equals.type(torch.FloatTensor))
        
        model.train()
        
        train_losses.append(running_loss/len(trainloader))
        test_losses.append(test_loss/len(testloader))

        print("Epoch: {}/{}.. ".format(e+1, epochs),
              "Training Loss: {:.3f}.. ".format(running_loss/len(trainloader)),
              "Test Loss: {:.3f}.. ".format(test_loss/len(testloader)),
              "Test Accuracy: {:.3f}".format(accuracy/len(testloader)))

查看训练后的误差损失对比

%matplotlib inline
%config InlineBackend.figure_format = 'retina'

import matplotlib.pyplot as plt

plt.plot(train_losses, label='Training loss')
plt.plot(test_losses, label='Validation loss')
plt.legend(frameon=False)

推理

# Import helper module (should be in the repo)
import helper

# Test out your network!

model.eval()

dataiter = iter(testloader)
images, labels = dataiter.next()
img = images[0]
# Convert 2D image to 1D vector
img = img.view(1, 784)

# Calculate the class probabilities (softmax) for img
with torch.no_grad():
    output = model.forward(img)

ps = torch.exp(output)

# Plot the image and probabilities
helper.view_classify(img.view(1, 28, 28), ps, version='Fashion')