Pytorch官方教程：快速上手训练自己的数据集

代码所使用的网络结构图：

1.数据集下载

#datesets.py(名称）


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))])

batch_size = 4

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
                                          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=batch_size,
                                         shuffle=False, num_workers=0)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

2.数据集查看

#show_.py(名称）

import torchvision
import matplotlib.pyplot as plt
import numpy as np
from datasets import trainloader, classes, batch_size
# 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()





if __name__ == "__main__":
   dataiter = iter(trainloader)
   images, labels = dataiter.next()
   imshow(torchvision.utils.make_grid(images))
   print('     '.join(f'{classes[labels[j]]:5s}' for j in range(batch_size)))

3.模型的主干网络

#model.py(名称）


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

class Net(nn.Module):
    def __init__(self):
        super().__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 = torch.flatten(x, 1) # flatten all dimensions except batch
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


          
net = Net()

4.模型的训练部分

#train.py(名称）


import torch
import torch.nn as nn
from datasets import trainloader
from model import net
import torch.optim as optim

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
print(device)
net.to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

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
        inputs, labels = data[0].to(device), data[1].to(device)
        # 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(f'[{epoch + 1}, {i + 1:5d}] loss: {running_loss / 2000:.3f}')
            running_loss = 0.0

print('Finished Training')
PATH = './cifar_net.pth'
torch.save(net.state_dict(), PATH)

5.预测模块

#prediction.py(名称）

import torch
import torchvision
from show_ import imshow
from datasets import testloader, classes
from model import net





dataiter = iter(testloader)
images, labels = dataiter.next()
imshow(torchvision.utils.make_grid(images))

print('GroundTruth: ', ' '.join(f'{classes[labels[j]]:5s}' for j in range(4)))

PATH = './cifar_net.pth'
net.load_state_dict(torch.load(PATH))
outputs = net(images)
_, predicted = torch.max(outputs, 1)

print('Predicted: ', ' '.join(f'{classes[predicted[j]]:5s}'
                              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(f'Accuracy of the network on the 10000 test images: {100 * correct // total} %')


# correct_pred = {classname: 0 for classname in classes}
# total_pred = {classname: 0 for classname in classes}


# with torch.no_grad():
#     for data in testloader:
#         images, labels = data
#         outputs = net(images)
#         _, predictions = torch.max(outputs, 1)
       
#         for label, prediction in zip(labels, predictions):
#             if label == prediction:
#                 correct_pred[classes[label]] += 1
#             total_pred[classes[label]] += 1



# for classname, correct_count in correct_pred.items():
#     accuracy = 100 * float(correct_count) / total_pred[classname]
#     print(f'Accuracy for class: {classname:5s} is {accuracy:.1f} %')