Python入門教程:訓練過程(分類爲例)

Python入門教程:訓練過程(分類爲例)

更多代碼和教程請參看:disanda.github.io 或 https://github.com/disanda

1.數據集操作

• Pillow和OpenCV常用於操作圖像
• scipy和librosa常用於操作語音
• NLTK and SpaCy常用於操作文本

torchvision.datasets and torch.utils.data.DataLoader包含了很大常用的數據集

本例使用cifar10數據集，其是32*32的數據集

2.訓練步驟

• 通過torchvision加載數據集，分割爲訓練數據集和測試數據集(一般5：1)
• 定義訓練網絡
• 定義損失函數
• 把訓練數據集導入網絡訓練參數
• 把測試數據集導入網絡查看結構

3.實現代碼

3.1 導入數據

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=0)

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')

3.2 查看數據

一個batch的大小，4張圖片

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)))

3.3 定義網絡

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()

3.4 定義損失函數

import torch.optim as optim

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

3.5 訓練網絡

最後把訓練後從參數保存到cifar_net.pth中

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

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
    #參數0代表從第一個開始
        # 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')

#Let’s quickly save our trained model:
PATH = './cifar_net.pth'
torch.save(net.state_dict(), PATH)

過程如下:

[1,  2000] loss: 2.264
[1,  4000] loss: 1.928
[1,  6000] loss: 1.706
[1,  8000] loss: 1.588
[1, 10000] loss: 1.539
[1, 12000] loss: 1.485
[2,  2000] loss: 1.411
[2,  4000] loss: 1.371
[2,  6000] loss: 1.350
[2,  8000] loss: 1.338
[2, 10000] loss: 1.302
[2, 12000] loss: 1.286
Finished Training

3.6 測試網絡

• 個別數據

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)))

net = Net()
net.load_state_dict(torch.load(PATH))
outputs = net(images)

_, predicted = torch.max(outputs, 1)

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

• 整個測試數據集

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))

• 不同類別的準確率

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]))

• 使用gpu

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

net.to(device)

inputs, labels = data[0].to(device), data[1].to(device)

https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html#sphx-glr-beginner-blitz-cifar10-tutorial-py