【Pytorch深度学习实践】刘二大人9多分类问题

输出不做激活，激活包含在CrossEntropyLoss()函数中，

CrossEntropyLoss = LogSoftmax + NLLLoss

推荐阅读：
NLL损失
交叉熵损失

#多分类问题一般采用softmax分类器
'''
import numpy as np
y=np.array([1,0,0])
z=np.array([0.2,0.1,-0.1])
y_pred=np.exp(z)/np.exp(z).sum()
loss=(-y*np.log(y_pred)).sum()
print(loss)
'''
#在使用交叉熵损失时，神经网络  最后一层不要做激活，因为已经包含在交叉熵损失里面了
'''
import torch
y=torch.LongTensor([0])
z=torch.Tensor([[0.2,0.1,-0.1]])
criterion=torch.nn.CrossEntropyLoss()
loss=criterion(z,y)
print(loss)
'''

#手写数字识别
import torch
from torchvision import transforms#对图像进行处理
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F#用relu
import torch.optim as optim

batch_size = 64
#把PIL转换成Tensor
transform = transforms.Compose([
    transforms.ToTensor(), #w*hc->c*w*h pytorch中能够更高效地进行处理
    transforms.Normalize((0.1307,), (0.3081,))])  # 归一化,均值和方差，使输入的像素值满足01分布

train_dataset = datasets.MNIST(root='../dataset/mnist/',
                               train=True,
                               download=True,
                               transform=transform)
train_loader = DataLoader(train_dataset,
                          shuffle=True,
                          batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/',
                              train=False,
                              download=True,
                              transform=transform)
test_loader = DataLoader(test_dataset,
                         shuffle=False,
                         batch_size=batch_size)


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)  # -1其实就是自动获取mini_batch
        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)  # 最后一层不做激活，不进行非线性变换


model = Net()

# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)


# training cycle forward, backward, update


def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        # 获得一个批次的数据和标签
        inputs, target = data
        optimizer.zero_grad()
        # 获得模型预测结果(64, 10)
        outputs = model(inputs)
        # 交叉熵代价函数outputs(64,10),target（64）
        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)  # dim = 1 列是第0个维度，行是第1个维度
            total += labels.size(0)
            correct += (predicted == labels).sum().item()  # 张量之间的比较运算
    print('accuracy on test set: %d %% ' % (100 * correct / total))


if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)