《PyTorch深度学习实战》第九讲

Softmax Classifier

传送门：https://www.bilibili.com/video/BV1Y7411d7Ys?p=9

多分类问题中，即要保证合理的模型预测，又要保证预测类别对其它类别的限制作用。

实现机理

Torch.nn.CrossEntropyloss函数机理

手写数据集模型框架

代码

import torch
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision import datasets
import torch.nn.functional as F
import torch.optim as optim
import matplotlib.pyplot as plt

#1.prepare dataset
#2.design model using class
#3.construct loss and optimizer
#4.training cycle+test

#1.准备数据集

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307, ), (0.3081, ))#均值，标准化
])
train_dataset = datasets.MNIST(root='./dataset/mnist',
                               train=True,
                               transform=transform,
                               download=True)
print(train_dataset[0])
test_dataset = datasets.MNIST(root='./dataset/mnist',
                              train=False,
                              transform=transform,
                              download=True)

train_loader = DataLoader(dataset=train_dataset,
                          batch_size=32,
                          shuffle=True)
test_loader = DataLoader(dataset=test_dataset,
                         batch_size=32,
                         shuffle=False)
#-----------------------线性模型------------------------
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.l1 = torch.nn.Linear(784, 512)
        self.l2 = torch.nn.Linear(512, 256)
        self.l3 = torch.nn.Linear(256,128)
        self.l4 = torch.nn.Linear(128, 64)
        self.l5 = torch.nn.Linear(64, 10)

    def forward(self, x):
        x = x.view(-1, 784)
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))
        return self.l5(x)
model = Net()
# 开启显卡
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

#3.构建loss和optimzer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

#4.循环
def train(epoch):
    running_loss = 0.0
    for batch_idx, (inputs, target) in enumerate(train_loader):
        inputs, target = inputs.to(device), target.to(device) #显卡加速

        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)

        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch+1, batch_idx+1, running_loss/300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
        print('Accuracy on test set: %d %%' % (100*correct / total))
    return correct / total

if __name__ == '__main__':
    epoch_list = []
    acc_list = []

    for epoch in range(10):
        train(epoch)
        acc = test()
        epoch_list.append(epoch)
        acc_list.append(acc)
        # if epoch % 10 == 9:
        #     test()
    import os
    os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'
    plt.plot(epoch_list, acc_list)
    plt.xlabel('epoch')
    plt.ylabel('accuracy')
    plt.show()