PyTorch Lecture11 Advanced CNN （Inception modules）(HKUST)

实现Inception modules

相关文章

使用GPU运算

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
batch_size = 64

# MNIST Dataset
train_dataset = datasets.MNIST(root='./data',
                               train=True,
                               transform=transforms.ToTensor(),
                               download=False)  #因为我已经下载过数据，所以download=False，如果你没下载过数据，请改为True

test_dataset = datasets.MNIST(root='./data',
                              train=False,
                              transform=transforms.ToTensor())
# Data Loader (Input Pipeline)

train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size,
                                          shuffle=False)


class InceptionA(nn.Module):
    def __init__(self, in_channels):
        super(InceptionA, self).__init__()
        self.branch1x1 = nn.Conv2d(in_channels, 16, kernel_size=1)
        self.branch5x5_1 = nn.Conv2d(in_channels, 16, kernel_size=1)
        self.branch5x5_1_2 = nn.Conv2d(16, 24, kernel_size=5, padding=2)

        self.branch3x3db1_1 = nn.Conv2d(in_channels, 16, kernel_size=1)
        self.branch3x3db1_2 = nn.Conv2d(16, 24, kernel_size=3, padding=1)
        self.branch3x3db1_3 = nn.Conv2d(24, 24, kernel_size=3, padding=1)

        self.branch_pool = nn.Conv2d(in_channels, 24, kernel_size=1)

    def forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch5x5 = self.branch5x5_1(x)
        branch5x5 = self.branch5x5_1_2(branch5x5)

        branch3x3db1 = self.branch3x3db1_1(x)
        branch3x3db1 = self.branch3x3db1_2(branch3x3db1)
        branch3x3db1 = self.branch3x3db1_3(branch3x3db1)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)
        outputs = [branch1x1, branch5x5, branch3x3db1, branch_pool]
        return torch.cat(outputs, 1)


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(88, 20, kernel_size=5)

        self.incept1 = InceptionA(in_channels=10)
        self.incept2 = InceptionA(in_channels=20)

        self.mp = nn.MaxPool2d(2)
        self.fc = nn.Linear(1408, 10)

    def forward(self, x):
        in_size = x.size(0)
        x = F.relu(self.mp(self.conv1(x)))
        x = self.incept1(x)
        x = F.relu(self.mp(self.conv2(x)))
        x = self.incept2(x)

        x = x.view(in_size, -1)  # flatten the tensor
        x = self.fc(x)
        return F.log_softmax(x)


model = Net()
model.cuda()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)


def train(epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = Variable(data).cuda(), Variable(target).cuda()
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % 10 == 0:
            print('Train Epoch:{}[{}/{} ({:.0f}%)]\t Loss:{:.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:
        data, target = Variable(data, volatile=True).cuda(), Variable(target).cuda()
        output = model(data)
        # sun up batch loss
        test_loss += F.nll_loss(output, target, size_average=False).data[0]
        # get the index of the max log-probability
        pred = torch.max(output.data, 1)[1].cuda()
        correct += pred.eq(target.data.view_as(pred)).sum()

    test_loss /= len(test_loader.dataset)
    print('\n Test 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, 10):
    train(epoch)
    test()