目录
- 一、实现过程
- 0、导包
- 1、准备数据
- 2、设计模型
- 3、构造损失函数和优化器
- 4、训练和测试
- 二、参考文献
一、实现过程
本文对经典手写数字数据集进行多分类,损失函数采用交叉熵,激活函数采用ReLU
,优化器采用带有动量的mini-batchSGD
算法。
所有代码如下:
0、导包
import torch from torchvision import transforms,datasets from torch.utils.data import DataLoader import torch.nn.functional as F import torch.optim as optim
1、准备数据
batch_size = 64 transform = transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.1307,),(0.3081,)) ]) # 训练集编程客栈 train_dataset = datasets.MNIST(root='G:/datasets/mnist',train=True,download=False,transform=transform) train_loader = DataLoader(train_dataset,shuffle=True,batch_size=batch_size) # 测试集 test_dataset = datasets.MNIST(root='G:/datasets/mnist',train=False,download=False,transform=transform) test_loader = DataLoader(test_dathttp://www.cppcns.comaset,shuffle=False,batch_size=batch_size)
2、设计模型
class Net(torch.nn.Module): def __init__(self): super(Net, self).__init__() self.l1 = torch.nn.Linear(784, 512) www.cppcns.comself.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() # 模型加载到GPU上 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") model.to(device)
3、构造损失函数和优化器
criterion = torch.nn.CrossEntropyLoss() optimizer = optim.SGD(model.parameters(),lr=0.01,momentum=0.5)
4、训练和测试
def train(epoch): running_loss = 0.0 for batch_idx, data in enumerate(train_loader, 0): inputs, target = data optimizer.zero_grad() # forward+backward+update outputs = model(inputs.to(device)) loss = criterion(outputs, target.to(device)) loss.backward() optimizer.step() running_loss += loss.item() if batch_idx % 300 == 299: print('[%d,%d] loss: %.3f' % (e编程客栈poch + 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.to(device)) _, predicted = torch.max(outputs.data, dim=1) total += labels.size(0) correct += (predicted.cpu() == labels).sum().item() print('Accuracy on test set: %d %%' % (100 * correct / total)) for epoch in range(10): train(epoch) test()
运行结果如下:
[1,300] loss: 2.166
[1,600] loss: 0.797[1,900] loss: 0.405Accuracy on test set: 90 %[2,300] loss: 0.303[2,600] loss: 0.252[2,900] loss: 0.218Accuracy on test set: 94 %[3,300] loss: 0.178[3,600] loss: 0.168[3,900] loss: 0.142Accuracy on test set: 95 %[4,300] loss: 0.129[4,600] loss: 0.119[4,900] loss: 0.110Accuracy on test set: 96 %[5,300] loss: 0.094[5,600] loss: 0.092[5,900] loss: 0.091Accuracy on test set: 96 %[6,300] loss: 0.077[6,600] loss: 0.070[6,900] loss: 0.075Accuracy on test set: 97 %[7,300] loss: 0.061[7,600] loss: 0.058[7,900] loss: 0.058Accuracy on test set: 97 %[8,300] loss: 0.043[8,600] loss: 0.051[8,900] loss: 0.050Accuracy on test set: 97 %[9,300] loss: 0.041[9,600] loss: 0.038[9,9编程客栈00] loss: 0.043Accuracy on test set: 97 %[10,300] loss: 0.030[10,600] loss: 0.032[10,900] loss: 0.033Accuracy on test set: 97 %
二、参考文献
- [1] https://www.bilibili.com/video/BV1Y7411d7Ys?p=9
到此这篇关于PyTorch手写数字数据集进行多分类的文章就介绍到这了,更多相关python多分类内容请搜索我们以前的文章或继续浏览下面的相关文章希望大家以后多多支持我们!
精彩评论