PyTorch学习（二）—— Linear regression、Logistic Regression、Softmax Classifier

原文链接： http://bit.ly/PyTorchZeroAll

一、Linear regression（in PyTorch way）

                 

import torch
from torch.autograd import Variable

# data define(3*1)
x_data = Variable(torch.Tensor([[1.0], [2.0], [3.0]]))
y_data = Variable(torch.Tensor([[2.0], [4.0], [6.0]]))

# model class
class Model(torch.nn.Module):
    def __init__(self):
        """
        In the constructor we instantiate two nn.Linear module
        """
        super(Model, self).__init__()
        self.linear = torch.nn.Linear(1, 1)  # one in and one out

    def forward(self, x):
        """
        In the forward function we accept a Variable of input data
        and we must return a Variable of output data. we can use modules
        defined in the constructor as well as arbitrary operator on Variable.
        """
        y_pred = self.linear(x)
        return y_pred

# our model
model = Model()

# construct our loss function and an optimizer.
# The call to model.parameters() in the SGD constructor will contain the learnable
# parameters of the two nn.Linear modules which are members of the model.
criterion = torch.nn.MSELoss(size_average=False)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# training loop
for epoch in range(500):
    # forward pass: compute predicted y by passing x to the model
    y_pred = model(x_data)

    # compute and print loss
    loss = criterion(y_pred, y_data)
    print(epoch, loss.item())

    # zero gradients, perform a backward pass, and update the weights
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

# after training -- test
hour_val = Variable(torch.Tensor([[4.0]]))
print("predict (after training)", 4, model.forward(hour_val).data[0][0])

import torch
import torch.nn as nn
from torch import optim
from torch.autograd import Variable
import torch.nn.functional as F
import torchvision
import torchvision.transforms as transform

#############################################################################
# 0. data loader
#############################################################################
transform = transform.Compose(
    [transform.ToTensor(), transform.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
)
train_set = torchvision.datasets.CIFAR10("./root", train=True, download=True, transform=transform)
train_loader = torch.utils.data.DataLoader(train_set, batch_size=4, shuffle=True, num_workers=0)
test_set = torchvision.datasets.CIFAR10("./root", train=False, download=True, transform=transform)
test_loader = torch.utils.data.DataLoader(test_set, batch_size=4, shuffle=False, num_workers=0)
classes = ("plane", "car", "bird", "cat", "deer", "dog", "frog", "horse", "ship", "trunk")

#############################################################################
# 1. define a neural network
# copy the neural network from the Neural Network section before and modify
# it to take 3-channel images(instead of 1-channel image as it was defined)
#############################################################################
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=6, kernel_size=5)
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv2 = nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5)
        self.fc1 = nn.Linear(in_features=16*5*5, out_features=120)
        self.fc2 = nn.Linear(in_features=120, out_features=84)
        self.fc3 = nn.Linear(in_features=84, out_features=10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16*5*5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)

        return x

net = Net()

#############################################################################
# 2. define a loss function and optimizer
# use a classification cross-entropy and SGD with momentum
#############################################################################
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

#############################################################################
# 3. train the network
# we simply have to loop over our data iterator,
# and feed the inputs to the network and optimize
#############################################################################
for epoch in range(2):
    running_loss = 0.0
    for i, data in enumerate(train_loader, 0):
        # get the inputs
        inputs, labels = data

        # warp them in Variable
        inputs, labels = Variable(inputs), Variable(labels)

        # zero the parameter gradient
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:
            print("[%d, %5d] loss: %.3f" %(epoch+1, i+1, running_loss/2000))
            running_loss = 0.0

print("Finished Training")

运行结果：

Files already downloaded and verified
Files already downloaded and verified
[1,  2000] loss: 2.229
[1,  4000] loss: 1.888
[1,  6000] loss: 1.665
[1,  8000] loss: 1.563
[1, 10000] loss: 1.507
[1, 12000] loss: 1.474
[2,  2000] loss: 1.413
[2,  4000] loss: 1.391
[2,  6000] loss: 1.345
[2,  8000] loss: 1.315
[2, 10000] loss: 1.299
[2, 12000] loss: 1.278
Finished Training

二、Logistic Regression 

import torch
import torch.nn as nn
from torch.autograd import Variable

# data define(4*1)
x_data = Variable(torch.Tensor([[1.0], [2.0], [3.0], [4.0]]))
y_data = Variable(torch.Tensor([[0.], [0.], [1.], [1.]]))

# model class
class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear = nn.Linear(1, 1)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        y_pred = self.sigmoid(self.linear(x))

        return y_pred

model = Model()

# loss function and optimizer
criterion = nn.BCELoss(size_average=True)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# training loop
for epoch in range(500):
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch, loss.item())

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

# test
hour_val = Variable(torch.Tensor([[0.5]]))
print("predict (after training)", 0.5, model.forward(hour_val).data[0][0])

运行结果：

三、Softmax Classifier

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch import optim
from torch.autograd import Variable
from torch.utils.data import Dataset, DataLoader
import torchvision
import torchvision.transforms as transforms

batch_size = 64
#############################################################################
# 0. data loader
#############################################################################
transform = transforms.Compose([
    transforms.ToTensor(), transforms.Normalize((0.1037, ), (0.3081,))])
train_set = torchvision.datasets.MNIST("../data", train=True, download=True, transform=transform)
train_loader = DataLoader(train_set, batch_size=batch_size, shuffle=True)
test_set = torchvision.datasets.MNIST("../data", train=False, download=True, transform=transform)
test_loader = DataLoader(test_set, batch_size=batch_size, shuffle=True)

#############################################################################
# 1. define a neural network
#############################################################################
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.l1 = nn.Linear(784, 520)
        self.l2 = nn.Linear(520, 320)
        self.l3 = nn.Linear(320, 240)
        self.l4 = nn.Linear(240, 120)
        self.l5 = nn.Linear(120, 10)
        
    def forward(self, x):
        x = x.view(-1, 784)  # flatten the data (n, 1, 28, 28)--> (n, 784)
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))
        x = F.relu(self.l5(x))
        
        return F.log_softmax(x)
    
model = Net()

optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

def train(epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = Variable(data), Variable(target)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % 10 == 0:
            print("Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss {:.6f}".format(
                epoch, batch_idx*len(data), len(train_loader.dataset),
                100.*batch_idx/len(train_loader), loss.item()))

def test():
    model.eval()
    test_loss = 0
    correct = 0
    for data, target in test_loader:
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        # sum up batch loss
        test_loss += F.nll_loss(output, target, size_average=False).item()
        # get the index of the max log-probability
        pred = output.data.max(1, keepdim=True)[1]
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()
    test_loss /= len(test_loader.dataset)

    print("\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n".format(
        test_loss, correct, len(test_loader.dataset), 100.*correct/len(test_loader.dataset)))

for epoch in range(1, 10):
    train(epoch)
    test()