pytorch教程实现mnist手写数字识别代码示例
更新时间:2021年09月07日 14:26:09 作者:xz1308579340
这篇文章主要讲解了pytorch教程中如何实现mnist手写数字识别,文中附有详细的代码示例,test准确率98%,有需要的朋友可以借鉴参考下
1.构建网络
nn.Moudle是pytorch官方指定的编写Net模块,在init函数中添加需要使用的层,在foeword中定义网络流向。
下面详细解释各层:
conv1层:输入channel = 1 ,输出chanael = 10,滤波器5*5
maxpooling = 2*2
conv2层:输入channel = 10 ,输出chanael = 20,滤波器5*5,
dropout
maxpooling = 2*2
fc1层:输入320 个神经单元,输出50个神经单元
fc1层:输入50个神经单元 ,输出10个神经单元
class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(1, 10, kernel_size=5) self.conv2 = nn.Conv2d(10, 20, kernel_size=5) self.conv2_drop = nn.Dropout2d() self.fc1 = nn.Linear(320, 50) self.fc2 = nn.Linear(50, 10) def forward(self, x): #x.size() = 28*28*1 x = F.relu(F.max_pool2d(self.conv1(x), 2)) x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2)) #x.size() =12*12*10 x = x.view(-1, 320) #x.size() =1*320 x = F.relu(self.fc1(x)) x = F.dropout(x, training=self.training) x = self.fc2(x) return F.log_softmax(x, dim=1)
2.编写训练代码
model = Net() #调用写好的网络 if args.cuda: #如果有GPU使用CPU model.cuda() optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum) #设置SGD随机梯度下降算法 def train(epoch): model.train() for batch_idx, (data, target) in enumerate(train_loader): if args.cuda: data, target = data.cuda(), target.cuda() data, target = Variable(data), Variable(target) optimizer.zero_grad() #梯度初始化为O output = model(data) loss = F.nll_loss(output, target) #简历loss function loss.backward() #反向传播,计算梯度 optimizer.step() #更新权重 if batch_idx % args.log_interval == 0: #输出信息 print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format( epoch, batch_idx * len(data), len(train_loader.dataset), 100. * batch_idx / len(train_loader), loss.data[0]))
3.编写测试代码
def test(): model.eval() test_loss = 0 correct = 0 for data, target in test_loader: if args.cuda: data, target = data.cuda(), target.cuda() data, target = Variable(data, volatile=True), Variable(target) output = model(data) test_loss += F.nll_loss(output, target, size_average=False).data[0] # sum up batch loss pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability correct += pred.eq(target.data.view_as(pred)).long().cpu().sum() test_loss /= len(test_loader.dataset) print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format( test_loss, correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
4.指导程序train和test
for epoch in range(1, args.epochs + 1): train(epoch) #训练N个epoch test() #检验在测试集上的表现
5.完整代码
# -*- coding: utf-8 -*- from __future__ import print_function import argparse import torch import torch.nn as nn import torch.nn.functional as F import torch.optim as optim from torchvision import datasets, transforms from torch.autograd import Variable # Training settings parser = argparse.ArgumentParser(description='PyTorch MNIST Example') parser.add_argument('--batch-size', type=int, default=64, metavar='N', help='input batch size for training (default: 64)') parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N', help='input batch size for testing (default: 1000)') parser.add_argument('--epochs', type=int, default=10, metavar='N', help='number of epochs to train (default: 10)') parser.add_argument('--lr', type=float, default=0.01, metavar='LR', help='learning rate (default: 0.01)') parser.add_argument('--momentum', type=float, default=0.5, metavar='M', help='SGD momentum (default: 0.5)') parser.add_argument('--no-cuda', action='store_true', default=False, help='disables CUDA training') parser.add_argument('--seed', type=int, default=1, metavar='S', help='random seed (default: 1)') parser.add_argument('--log-interval', type=int, default=10, metavar='N', help='how many batches to wait before logging training status') args = parser.parse_args() args.cuda = not args.no_cuda and torch.cuda.is_available() torch.manual_seed(args.seed) if args.cuda: torch.cuda.manual_seed(args.seed) kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {} train_loader = torch.utils.data.DataLoader( datasets.MNIST('../data', train=True, download=True, transform=transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,)) ])), batch_size=args.batch_size, shuffle=True, **kwargs) test_loader = torch.utils.data.DataLoader( datasets.MNIST('../data', train=False, transform=transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,)) ])), batch_size=args.test_batch_size, shuffle=True, **kwargs) class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(1, 10, kernel_size=5) self.conv2 = nn.Conv2d(10, 20, kernel_size=5) self.conv2_drop = nn.Dropout2d() self.fc1 = nn.Linear(320, 50) self.fc2 = nn.Linear(50, 10) def forward(self, x): print (x.size()) x = F.relu(F.max_pool2d(self.conv1(x), 2)) print(x.size()) x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2)) print(x.size()) x = x.view(-1, 320) x = F.relu(self.fc1(x)) x = F.dropout(x, training=self.training) x = self.fc2(x) return F.log_softmax(x, dim=1) model = Net() #调用写好的网络 if args.cuda: #如果有GPU使用CPU model.cuda() optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum) #设置SGD随机梯度下降算法 def train(epoch): model.train() for batch_idx, (data, target) in enumerate(train_loader): if args.cuda: data, target = data.cuda(), target.cuda() data, target = Variable(data), Variable(target) optimizer.zero_grad() #梯度初始化为O output = model(data) loss = F.nll_loss(output, target) #简历loss function loss.backward() #反向传播,计算梯度 optimizer.step() #更新权重 if batch_idx % args.log_interval == 0: #输出信息 print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format( epoch, batch_idx * len(data), len(train_loader.dataset), 100. * batch_idx / len(train_loader), loss.data[0])) def test(): model.eval() test_loss = 0 correct = 0 for data, target in test_loader: if args.cuda: data, target = data.cuda(), target.cuda() data, target = Variable(data, volatile=True), Variable(target) output = model(data) test_loss += F.nll_loss(output, target, size_average=False).data[0] # sum up batch loss pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability correct += pred.eq(target.data.view_as(pred)).long().cpu().sum() test_loss /= len(test_loader.dataset) print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format( test_loss, correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset))) for epoch in range(1, args.epochs + 1): train(epoch) test()
以上就是pytorch教程实现mnist手写数字识别代码示例的详细内容,更多关于pytorch实现mnist手写数字识别的资料请关注脚本之家其它相关文章!
最新评论