pytorch入门学习：训练一个图像分类器

0 将做以下工作：

1. 采用torchvision来下载CIFAR10的训练和测试集
2. 定义一个卷积神经网络
3. 定义损失函数
4. 采用训练集来训练网络
5. 采用测试集

1 下载训练集和测试集

Using ``torchvision``, it’s extremely easy to load CIFAR10.
"""
import torch
import torchvision
import torchvision.transforms as transforms

########################################################################
# The output of torchvision datasets are PILImage images of range [0, 1].
# We transform them to Tensors of normalized range [-1, 1].

transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])  # 前面的0.5是均值，后面的0.5是方差

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,  # 将已有的数据按照batch size封装成Tensor
                                          shuffle=True, num_workers=0)  # num_workers，采用几个线程来导入数据，0表示采用主线程；# shuffle，一般在训练数据中会采用。


testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                         shuffle=False, num_workers=0)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

########################################################################
# Let us show some of the training images, for fun.

import matplotlib.pyplot as plt
import numpy as np

# functions to show an image


def imshow(img):
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))


# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()

# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))

输出：

2 定义卷积神经网络

代码：

########################################################################
# 2. Define a Convolution Neural Network
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# Copy the neural network from the Neural Networks section before and modify it to
# take 3-channel images (instead of 1-channel images as it was defined).

import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 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()

print(net)
# 输出网络看一下参数
params = list(net.parameters())
print(len(params))
for i in range(len(params)):
    print(i, ' : ', params[i].size())

输出：

3 定义损失函数和优化器

import torch.optim as optim

criterion = nn.CrossEntropyLoss()  # 定义损失函数为交叉熵损失函数
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)  # 采用SGD（随机梯度下降法）

4 训练

########################################################################
# 4. Train the network
# ^^^^^^^^^^^^^^^^^^^^
#
# This is when things start to get interesting.
# We simply have to loop over our data iterator, and feed the inputs to the
# network and optimize.

for epoch in range(2):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0): # enumerate()函数把一个可遍历的数据对象组合为一个索引序列，一般用于for循环中
        # get the inputs
        inputs, labels = data

        # zero the parameter gradients
        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 every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

注意：
epoch（纪元）：对所有图像样本训练几遍
iter（迭代）：这个和batch_size、sample_num有关系
batch_size：一次迭代要训练几张图片
iter*batch_size = sample_num

输出：

5 测试

########################################################################
# 5. Test the network on the test data
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#
# We have trained the network for 2 passes over the training dataset.
# But we need to check if the network has learnt anything at all.
#
# We will check this by predicting the class label that the neural network
# outputs, and checking it against the ground-truth. If the prediction is
# correct, we add the sample to the list of correct predictions.
#
# Okay, first step. Let us display an image from the test set to get familiar.

# dataiter = iter(testloader)
# images, labels = dataiter.next()
# 
# # print images
# imshow(torchvision.utils.make_grid(images))
# print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))

########################################################################
# Okay, now let us see what the neural network thinks these examples above are:

# outputs = net(images)

########################################################################
# The outputs are energies for the 10 classes.
# Higher the energy for a class, the more the network
# thinks that the image is of the particular class.
# So, let's get the index of the highest energy:
# _, predicted = torch.max(outputs, 1)
#
# print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
#                               for j in range(4)))

########################################################################
# The results seem pretty good.
#
# Let us look at how the network performs on the whole dataset.

correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
                                      for j in range(4)))
        print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
    100 * correct / total))

输出：

下面是输出各类的准确率：

########################################################################
# That looks waaay better than chance, which is 10% accuracy (randomly picking
# a class out of 10 classes).
# Seems like the network learnt something.
#
# Hmmm, what are the classes that performed well, and the classes that did
# not perform well:

class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs, 1)
        c = (predicted == labels).squeeze()
        for i in range(4):
            label = labels[i]
            class_correct[label] += c[i].item()
            class_total[label] += 1


for i in range(10):
    print('Accuracy of %5s : %2d %%' % (
        classes[i], 100 * class_correct[i] / class_total[i]))

输出：

在GPU上跑？

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# Assume that we are on a CUDA machine, then this should print a CUDA device:

print(device)

net.to(device)
inputs, labels = inputs.to(device), labels.to(device)