pytorch整理（二）

数据

当必须处理图像、文本、音频或视频数据时，可以使用python标准库将数据加载到numpy数组里。然后将这个数组转化成torch.*Tensor。

对于图片，有Pillow，OpenCV等包可以使用
对于音频，有scipy和librosa等包可以使用
对于文本，不管是原生python的或者是基于Cython的文本，可以使用NLTK和SpaCy

对于视觉方面，我们创建了一个包，名字叫torchvision，其中包含了针对Imagenet、CIFAR10、MNIST等常用数据集的数据加载器(data loaders），还有对图片数据变形的操作，即torchvision.datasets和torch.utils.data.DataLoader。

图片分类器

数据

CIFAR-10如下的分类：“飞机”，“汽车”，“鸟”，“猫”，“鹿”，“狗”，“青蛙”，“马”，“船”，“卡车”等，图片数据大小是3x32x32。

import torch
import torchvision
import torchvision.transforms as transforms
transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))])
# torchvision数据集加载完后的输出是范围在[0, 1]之间的PILImage。我们将其标准化为范围在[-1, 1]之间的张量:image = (image - mean) / std
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')

可视化部分数据

import matplotlib.pyplot as plt
import numpy as np

# 输出图像的函数
def imshow(img):
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()

# 随机获取训练图片
dataiter = iter(trainloader)
images, labels = dataiter.next()

# 显示图片
imshow(torchvision.utils.make_grid(images))#多图片集合成一张
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))

torchvision.utils.make_grid(tensor, nrow=8, padding=2, normalize=False, range=None, scale_each=False, pad_value=0）
tensor (Tensor or list) – 4D mini-batch Tensor of shape (B x C x H x W) or a list of images all of the same size.
nrow (int, optional) – 每一行显示的图像数. 最终图标尺寸为(B / nrow, nrow). 默认为8.
padding (int, optional) –填充. Default is 2.
normalize (bool, optional) – If True, 归一化图像到(0, 1)区间, by subtracting the minimum and dividing by the maximum pixel value.
range (tuple, optional) – tuple (min, max) where min and max are numbers, then these numbers are used to normalize the image. By default, min and max are computed from the tensor.
scale_each (bool, optional) – If True, scale each image in the batch of images separately rather than the (min, max) over all images.
pad_value (float, optional) – Value for the padded pixels.

torchvision.utils.save_image(tensor, filename, nrow=8, padding=2, normalize=False, range=None, scale_each=False, pad_value=0)

网络

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()

损失函数和优化器

import torch.optim as optim

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

训练网络

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
        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()# 计算一个epoch的平均值
        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')

测试

torch.max(a,1) 返回每一行中最大值的那个元素，且返回其索引（返回最大元素在这一行的列索引）

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))

GPU

torch.device(‘cuda:0’)
torch.device(‘cpu’)
torch.randn((2,3), ‘cuda:1’)

多GPU

os.environ[‘CUDA_VISIBLE_DEVICES’] = ‘0,3’
程序开始用来限制GPU
推荐DistributedDataParallel

device = torch.device("cuda: 0")
model.to(device)
mytensor = my_tensor.to(device)

模拟程序

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

# Parameters 和 DataLoaders
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("\tIn Model: input size", input.size(),
              "output size", output.size())
        return output

model = Model(input_size, output_size)
if torch.cuda.device_count() > 1: 
  print("Let's use", torch.cuda.device_count(), "GPUs!")
  # dim = 0 [30, xxx] -> [10, ...], [10, ...], [10, ...] on 3 GPUs
  model = nn.DataParallel(model)#默认全部GPU
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())

训练与保存

保存、加载
多GPU的模型会多module这个关键字

使用远程服务器训练，而且没有图形界面。在使用matplotlib绘图时，建议添加以下代码：

import matplotlib.pyplot as plt
plt.switch_backend('agg')

训练时不要使用plt.show()，只是保存图片就行，之后在下载就可以。