Pytorch學習---訓練一個分類器

Python小TIPS

class_correct = list(0. for i in range(10))
class_total   = list(0. for i in range(10))
# class_correct [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]

 

一般情況下處理圖像、文本、音頻和視頻數據時，可以使用標準的Python包來加載數據到一個numpy數組中。然後把這個數組轉換成 ``torch.*Tensor``。

• -  圖像可以使用 Pillow, OpenCV
• -  音頻可以使用 scipy, librosa
• -  文本可以使用原始Python和Cython來加載，或者使用 NLTK或 SpaCy 處理

對於圖像而言，我們採用了我們創建了一個包``torchvision``，它包含了處理一些基本圖像數據集的方法。這些數據集包括
Imagenet, CIFAR10, MNIST 等。除了數據加載以外，``torchvision`` 還包含了圖像轉換器，``torchvision.datasets`` 和 ``torch.utils.data.DataLoader``。

 

CIFAR10包含10個類

‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’。

CIFAR-10的圖像都是 3x32x32大小的，即，3顏色通道，32x32像素。

依次按照下列順序進行：

• 1. 使用``torchvision``加載和歸一化CIFAR10訓練集和測試集
• 2. 定義一個卷積神經網絡
• 3. 定義損失函數
• 4. 在訓練集上訓練網絡
• 5. 在測試集上測試網絡

import torch
import torchvision
import torchvision.transforms as transforms
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
# print('class_correct',class_correct)

# torchvision的輸出是[0,1]的PILImage圖像，我們把它轉換爲歸一化範圍爲[-1, 1]的張量。
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')


import matplotlib.pyplot as plt
import numpy as np
# 展示圖像的函數
def imshow(img):
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
# 獲取隨機數據
dataiter = iter(trainloader)
images, labels = dataiter.next()

# 展示圖像
imshow(torchvision.utils.make_grid(images))
# 顯示圖像標籤
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))



# 2  定義一個卷積神經網絡
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. 定義損失函數和優化器我們使用交叉熵作爲損失函數，使用帶動量的隨機梯度下降。
import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

# 4. 訓練網路有趣的時刻開始了。 我們只需在數據迭代器上循環，將數據輸入給網絡，並優化。
for epoch in range(2):  # 多批次循環

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # 獲取輸入
        inputs, labels = data

        # 梯度置0
        optimizer.zero_grad()

        # 正向傳播，反向傳播，優化
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # 打印狀態信息
        running_loss += loss.item()
        if i % 2000 == 1999:    # 每2000批次打印一次
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

# 5 在測試集上測試網絡
dataiter = iter(testloader)
images, labels = dataiter.next()

# 顯示圖片
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]))