pytorch 官方教程（一）

1、简单torch的使用

# -*- coding: utf-8 -*-
from __future__ import print_function
import torch
x = torch.rand(5, 3)
print(x)
x = torch.zeros(5, 3, dtype=torch.long)
print(x)

x = torch.tensor([5.5, 3])
print(x)

x = x.new_ones(5, 3, dtype=torch.double)
# new_* methods take in sizes
print(x)

x = torch.randn_like(x, dtype=torch.float)
# override dtype!
print(x)
# result has the same size
print(x.size())

y = torch.rand(5, 3)
print(x + y)
print(torch.add(x, y))

result = torch.empty(5, 3)
torch.add(x, y, out=result)
print("result:\n", result)

# add: in-place
# adds x to y
y.add_(x)
print("y:\n", y)

print(x[:, 1])

# 改变tensor大小或形状
x = torch.randn(4, 4)
y = x.view(16)
z = x.view(-1, 8)  # the size -1 is inferred from other dimensions
print(x.size(), y.size(), z.size())

x = torch.randn(1)
print(x)
print(x.item())

2、torch的简单运算

import torch

x = torch.ones(2, 2, requires_grad=True)
print(x)

y = x + 2
print(y)
print(y.grad_fn)

z = y * y * 3
out = z.mean()
print(z, out)


a = torch.randn(2, 2)
a = ((a * 3) / (a - 1))
print(a.requires_grad)

a.requires_grad_(True)
print(a.requires_grad)
b = (a * a).sum()
print(b.grad_fn)
out.backward()
print(x.grad)

x = torch.randn(3, requires_grad=True)
y = x * 2
while y.data.norm() < 1000:
    y = y * 2

print(y)

v = torch.tensor([0.1, 1.0, 0.0001], dtype=torch.float)
y.backward(v)
print(x.grad)

print(x.requires_grad)
print((x**2).requires_grad)

with torch.no_grad():
    print((x**2).requires_grad)

3、torch组织简单网络

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

class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        #  1 input image channel, 6 output, 5×5 square convolution
        #  kernel
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        #  an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        #  Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        #  If the size is a square you can only specify a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features


net = Net()
print(net)
params = list(net.parameters())
print(len(params))
print(params[0].size())
input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)
net.zero_grad()
out.backward(torch.randn(1, 10))

output = net(input)
target = torch.randn(10)  # a dummy target, for example
target = target.view(1, -1)  # make it the same shape as output
criterion = nn.MSELoss()

loss = criterion(output, target)
print("loss", loss)
print(loss.grad_fn)  # MSELoss
print(loss.grad_fn.next_functions[0][0])  # Linear
print(loss.grad_fn.next_functions[0][0].next_functions[0][0])

net.zero_grad()  # zeros the gradient buffers of all parameters

print('conv1.bias.grad before backward')
print(net.conv1.bias.grad)

loss.backward()

print('conv1.bias.grad after backward')
print(net.conv1.bias.grad)

learning_rate = 0.01
for f in net.parameters():
    f.data.sub_(f.grad.data * learning_rate)



import torch.optim as optim

# create your optimizer
optimizer = optim.SGD(net.parameters(), lr=0.01)

# in your training loop:
optimizer.zero_grad()  # zero the gradient buffers
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()  # Does the update

4、加载图像数据

import torch
import torchvision
import torchvision.transforms as transforms

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', 'trunk')


import matplotlib.pyplot as plt
import numpy as np
# functions to show an image

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


if __name__ == '__main__':
    # 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)))

5、简单训练

import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import matplotlib.pyplot as plt
import numpy as np

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=False, 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=False, 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', 'trunk')


# 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()




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


if __name__ == '__main__':
    net = Net()
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

    for epoch in range(2): #  loop over the dataset multiple
        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            # get the inputs
            inputs, labels = data
            # zero the parameter grasents
            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')

    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)))

    outputs = net(images)
    _, predicted = torch.max(outputs, 1)
    print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4)))

    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))

    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]))

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

6、数据并行

import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader

input_size = 5
output_size = 2

batch_size = 30
data_size = 100

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


class RandomDataset(Dataset):

    def __init__(self, size, length):
        self.len = length
        self.data = torch.randn(length, size)

    def __getitem__(self, index):
        return self.data[index]

    def __len__(self):
        return self.len


rand_loader = DataLoader(dataset=RandomDataset(input_size, data_size), batch_size=batch_size, shuffle=True)


class Model(nn.Module):
    # Our model

    def __init__(self, input_size, output_size):
        super(Model, self).__init__()
        self.fc = nn.Linear(input_size, output_size)

    def forward(self, input):
        output = self.fc(input)
        print("\t In Model: input_size", input.size(), "output_size", output.size())
        return output


model = Model(input_size, output_size)
if torch.cuda.device_count() > 0:
    print("Let's use", torch.cuda.device_count(), "GPUs!")
    # dim = 0 [30, xxx] ->[10, ...], [10, ...],[10, ...] on 3 GPUs
    model = nn.DataParallel(model)

model.to(device)

for data in rand_loader:
    input = data.to(device)
    output = model(input)
    print("Outside: input_size", input.size(), "output_size", output.size())
    

7、Pytorch之数据加载和处理

from __future__ import print_function, division
import os
import torch
import pandas as pd  # 用于更容易地进行csv解析
from skimage import io, transform  # 用于图像的IO和变换
import numpy as np
import matplotlib.pyplot as plt
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils

# 忽略警告
import warnings
warnings.filterwarnings("ignore")

plt.ion()  # interactive mode

landmarks_frame = pd.read_csv('data/faces/face_landmarks.csv')

n = 65
img_name = landmarks_frame.iloc[n, 0]
landmarks = landmarks_frame.iloc[n, 1:].as_matrix()
landmarks = landmarks.astype('float').reshape(-1, 2)

print('Image name: {}'.format(img_name))
print('Landmark shape: []'.format(landmarks.shape))
print('First 4 Landmarks: {}'.format(landmarks[:4]))

# 4 编写函数

def show_landmarks(image, landmarks):
    """显示带有地标的图片"""
    plt.imshow(image)
    plt.scatter(landmarks[:, 0], landmarks[:, 1], s=10, marker='.', c='r')
    plt.pause(0.001)  # pause a bit so that plots are updated


plt.figure()
show_landmarks(io.imread(os.path.join('data/faces/', img_name)), landmarks)
plt.show()

# 5 建立数据集类

class FaceLandmarksDataset(Dataset):
    """面部标记数据集。"""

    def __init__(self, csv_file, root_dir, transform=None):
        """

        :param csv_file[string]: 带注释的csv文件的路径。
        :param root_dir[string]: 包含所有图片的目录。
        :param transform[callable, optional]: 一个样本上的可用的可选变换
        """
        self.landmarks_frame = pd.read_csv(csv_file)
        self.root_dir = root_dir
        self.transform = transform

    def __len__(self):
        return len(self.landmarks_frame)

    def __getitem__(self, idx):
        img_name = os.path.join(self.root_dir, self.landmarks_frame.iloc[idx, 0])
        image = io.imread(img_name)
        landmarks = self.landmarks_frame.iloc[idx, 1:]
        landmarks = np.array([landmarks])
        landmarks = landmarks.astype('float').reshape(-1, 2)
        sample = {'image': image, 'landmarks': landmarks}

        if self.transform:
            sample = self.transform(sample)

        return sample


# 6 数据可视化
face_dataset = FaceLandmarksDataset(csv_file='data/faces/face_landmarks.csv', root_dir='data/faces')
fig = plt.figure()
for i in range(len(face_dataset)):
    sample = face_dataset[i]
    print(i, sample['image'].shape, sample['landmarks'].shape)
    ax = plt.subplot(1, 4, i + 1)
    plt.tight_layout()
    ax.set_title('Sample #{}'.format(i))
    ax.axis('off')
    show_landmarks(**sample)

    if i == 3:
        plt.show()
        break


# 7 数据变换
# tsfm = transform(params)
# transformed_sample = tsfm(sample)
class Rescale(object):
    """"将样本中的图像重新缩放到给定大小
    Args:
        output_size (tuple或int):所需的输出大小。如果是元组，则输出为与output_size匹配。
        如果是int，则匹配较小的图像边缘到output_size保持纵横比相同.
    """
    def __init__(self, output_size):
        assert isinstance(output_size, (int, tuple))
        self.output_size = output_size

    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']

        h, w = image.shape[:2]
        if isinstance(self.output_size, int):
            if h > w:
                new_h, new_w = self.output_size * h / w, self.output_size
            else:
                new_h, new_w = self.output_size, self.output_size * w / h
        else:
            new_h, new_w = self.output_size

        new_h, new_w = int(new_h), int(new_w)
        img = transform.resize(image, (new_h, new_w))
        # h and w are swapped for landmarks because for images.
        # x and y axes are axis 1 and 0 respectively
        landmarks = landmarks * [new_w / w, new_h / h]
        return {'image':img, 'landmarks':landmarks}


class RandomCrop(object):
    """
    随机裁剪样本中的图像
    Args：
        output_size(tuple或int):所需的输出大小。如果是int，方形裁剪是。

    """
    def __init__(self, output_size):
        assert isinstance(output_size, (int, tuple))
        if isinstance(output_size, int):
            self.output_size = (output_size, output_size)
        else:
            assert len(output_size) == 2
            self.output_size = output_size

    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']

        h, w = image.shape[:2]
        new_h, new_w = self.output_size
        top = np.random.randint(0, h - new_h)
        left = np.random.randint(0, w - new_w)

        image = image[top: top + new_h, left: left + new_w]
        landmarks = landmarks - [left, top]

        return {'image': image, 'landmarks': landmarks}


class ToTensor(object):
    """将样本中的ndarrays转换为Tensors. """
    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']

        # 交换颜色轴，因为
        # numpy包的图片是：H * W * C
        # torch包的图片是：C * H * W
        image = image.transpose((2, 0, 1))
        return {'image': torch.from_numpy(image), 'landmarks': torch.from_numpy(landmarks)}


# 8 组合转换

scale = Rescale(256)
crop = RandomCrop(128)
composed = transforms.Compose([Rescale(256), RandomCrop(224)])

# 在样本上应用上述的每个变换
fig = plt.figure()
sample = face_dataset[65]
for i, tsfm in enumerate([scale, crop, composed]):
    transformed_sample = tsfm(sample)

    ax = plt.subplot(1, 3, i + 1)
    plt.tight_layout()
    ax.set_title(type(tsfm).__name__)
    show_landmarks(**transformed_sample)
    plt.show()

#  input()  # 仅用来等待

# 9 迭代数据集

transformed_dataset = FaceLandmarksDataset(csv_file='data/faces/face_landmarks.csv', root_dir='data/faces/',
                                           transform=transforms.Compose([Rescale(256), RandomCrop(224), ToTensor()]))
for i in range(len(transformed_dataset)):
    sample = transformed_dataset[i]
    print(i, sample['image'].size(), sample['landmarks'].size())
    if i == 3:
        break

# input()

dataloader = DataLoader(transformed_dataset, batch_size=4, shuffle=True, num_workers=4)

# 辅助功能：显示批次
def show_landmarks_batch(sample_batched):
    """ Show image with landmarks for a batch of samples."""
    images_batch, landmarks_batch = sample_batched['image'], sample_batched['landmarks']
    batch_size = len(images_batch)
    im_size = images_batch.size(2)
    grid_border_size = 2

    grid = utils.make_grid(images_batch)
    plt.imshow(grid.numpy().transpose((1, 2, 0)))

    for i in range(batch_size):
        plt.scatter(landmarks_batch[i, :, 0].numpy() + i * im_size + (i + 1) * grid_border_size,
                    landmarks_batch[i, :, 1].numpy() + grid_border_size, s=10, marker='.', c='r')
        plt.title('Batch from dataloader')


if __name__ == '__main__':
    for i_batch, sample_batched in enumerate(dataloader):
        print(i_batch, sample_batched['image'].size(), sample_batched['landmarks'].size())
        # 观察第4批次并停止
        if i_batch == 3:
            plt.figure()
            show_landmarks_batch(sample_batched)
            plt.axis('off')
            plt.ioff()
            plt.show()
            break