基于PyTorch的深度学习入门教程_cifar10_tutorial

摘要

"""
训练一个分类器
= = = = = = = = = = = = = = = = = = = = =

您已经了解了如何定义神经网络、计算损失和更新网络的权重。

现在你可能会想，

数据呢?
----------------

通常，当必须处理图像、文本、音频或视频数据时，可以使用标准python包将数据加载到numpy数组中。然后你可以把这个数组转换成一个torch.*Tensor。

-对于图片，包如Pillow, OpenCV是有用的
-对于音频，包如scipy和librosa
-对于文本，无论是原始Python或基于Cython的加载，还是NLTK和SpaCy都是有用的

特别针对vision，我们创建了一个名为“torchvision”的包，其中包含用于Imagenet、CIFAR10、MNIST等常见数据集的数据加载器，以及用于image的数据转换器，即'torchvision.datasets'和' ' torch.utils.data.DataLoader”。

这提供了极大的便利，避免了编写样板代码。

在本教程中，我们将使用CIFAR10数据集。
它有几个类:“飞机”、“汽车”、“鸟”、“猫”、“鹿”，“狗”、“青蛙”、“马”、“船”、“卡车”。CIFAR-10中的图像是尺寸为3x32x32，即大小为32x32像素的3通道彩色图像。

.. figure:: /_static/img/cifar10.png
   :alt: cifar10

cifar10

训练图像分类器
----------------------------

我们将按照以下步骤进行:

1. 使用“torchvision”加载和标准化CIFAR10训练和测试数据集
2. 定义卷积神经网络
3.定义一个损失函数
4. 根据训练数据对网络进行训练
5. 用测试数据测试网络
"""

#1. 加载和正则化CIFAR10
#^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^

#使用'torchvision'，非常容易加载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))])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                          shuffle=True, num_workers=2)

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=2)

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)))
    plt.show()


# 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)))


########################################################################
# 2. Define a Convolutional Neural Network
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# 从之前的神经网络部分复制神经网络，修改成3通道的图像(而不是定义的1通道图像)。

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()

########################################################################
# 3. Define a Loss function and optimizer
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# Let's use a Classification Cross-Entropy loss and SGD with momentum.

import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

########################################################################
# 4. Train the network
# ^^^^^^^^^^^^^^^^^^^^
# 这是事情开始变得有趣的时候。我们只需遍历数据迭代器，并将输入输入到网络并进行优化。

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

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs; data is a list of [inputs, labels]
        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')

########################################################################
# 5. Test the network on the test data
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#
#我们对网络进行了两次遍历训练数据集的训练。但我们需要检查该网络是否有所收获。
#我们将通过预测神经网络输出的类标签来检查这一点，并根据基本事实来检查它。
#如果预测是正确的，我们将样本添加到正确预测列表中。
#好的,第一步。让我们从测试集中显示一个图像来熟悉它。

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)

########################################################################
# 输出是这10个类的能量。
# 类的能量越高，网络越认为图像属于特定的类。
# 所以，让我们来看看最高能量指数:
_, predicted = torch.max(outputs, 1)

print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
                              for j in range(4)))

########################################################################
# The results seem pretty good.
#
# 让我们看看网络如何在整个数据集上执行。

correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

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

########################################################################
# 这看起来比随机抽取10%的正确率(从10个类中随机抽取一个类)要好得多。
# 似乎网络学到了一些东西。
# Hmmm，哪些类执行得好，哪些类执行得不好:

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]))

########################################################################
# 好的，接下来呢?
# 我们如何在GPU上运行这些神经网络?
# Training on GPU
# - - - - - - - - - - - - - - - - -
# 就像你把张量转移到GPU上一样，你把神经网络转移到GPU上。
# 如果我们有cuda可用,让我们首先定义我们的设备为第一个可见的cuda设备:

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

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

print(device)

########################################################################
# The rest of this section assumes that ``device`` is a CUDA device.
#
# Then these methods will recursively go over all modules and convert their
# parameters and buffers to CUDA tensors:
#
# .. code:: python
#
#     net.to(device)
#
#
# Remember that you will have to send the inputs and targets at every step
# to the GPU too:
#
# .. code:: python
#
#         inputs, labels = data[0].to(device), data[1].to(device)
#
# Why dont I notice MASSIVE speedup compared to CPU? Because your network
# is realllly small.
#
# **Exercise:** Try increasing the width of your network (argument 2 of
# the first ``nn.Conv2d``, and argument 1 of the second ``nn.Conv2d`` –
# they need to be the same number), see what kind of speedup you get.
#
# **Goals achieved**:
#
# - Understanding PyTorch's Tensor library and neural networks at a high level.
# - Train a small neural network to classify images
#
# Training on multiple GPUs
# -------------------------
# If you want to see even more MASSIVE speedup using all of your GPUs,
# please check out :doc:`data_parallel_tutorial`.
#
# Where do I go next?
# -------------------
#
# -  :doc:`Train neural nets to play video games </intermediate/reinforcement_q_learning>`
# -  `Train a state-of-the-art ResNet network on imagenet`_
# -  `Train a face generator using Generative Adversarial Networks`_
# -  `Train a word-level language model using Recurrent LSTM networks`_
# -  `More examples`_
# -  `More tutorials`_
# -  `Discuss PyTorch on the Forums`_
# -  `Chat with other users on Slack`_
#
# .. _Train a state-of-the-art ResNet network on imagenet: https://github.com/pytorch/examples/tree/master/imagenet
# .. _Train a face generator using Generative Adversarial Networks: https://github.com/pytorch/examples/tree/master/dcgan
# .. _Train a word-level language model using Recurrent LSTM networks: https://github.com/pytorch/examples/tree/master/word_language_model
# .. _More examples: https://github.com/pytorch/examples
# .. _More tutorials: https://github.com/pytorch/tutorials
# .. _Discuss PyTorch on the Forums: https://discuss.pytorch.org/
# .. _Chat with other users on Slack: https://pytorch.slack.com/messages/beginner/

# %%%%%%INVISIBLE_CODE_BLOCK%%%%%%
del dataiter
# %%%%%%INVISIBLE_CODE_BLOCK%%%%%%