STN网络官方文档复现

写在前面：目前在学习pytorch官方文档的内容，以此来记录自己的学习过程，本次学习的是STN网络。
传送门：官方文档
中文翻译
STN论文链接（Spatial Transformer Networks ）
为什么要用到STN网络呢：
卷积神经网络定义了一个异常强大的模型类，但在计算和参数有效的方式下仍然受限于对输入数据的空间不变性。在此引入了一个新的可学模块，空间变换网络，它显式地允许在网络中对数据进行空间变换操作。这个可微的模块可以插入到现有的卷积架构中，使神经网络能够主动地在空间上转换特征映射，在特征映射本身上有条件，而不需要对优化过程进行额外的训练监督或修改。我们展示了空间变形的使用结果，在模型中学习了平移、缩放、旋转和更一般的扭曲，结果在几个基准上得到了很好的效果。

数学理论知识见论文。

代码如下：

from __future__ import print_function
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision
from torchvision import datasets, transforms
import matplotlib.pyplot as plt
import numpy as np

plt.ion()

train_loader = torch.utils.data.DataLoader(
    datasets.MNIST(root='.', train=True, download=True, transform=transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.1307,), (0.3081,))
    ])), batch_size=64, shuffle=True, num_workers=4
)

test_loader = torch.utils.data.DataLoader(
    datasets.MNIST(root='.', train=False, transform=transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.1307,), (0.3081,))
    ])), batch_size=64, shuffle=True, num_workers=4
)

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

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)

        self.localization = nn.Sequential(
            nn.Conv2d(1, 8, kernel_size=7),
            nn.MaxPool2d(2, stride=2),
            nn.ReLU(True),
            nn.Conv2d(8, 10, kernel_size=5),
            nn.MaxPool2d(2, stride=2),
            nn.ReLU(True)
        )

        self.fc_loc = nn.Sequential(
            nn.Linear(10 * 3 * 3, 32),
            nn.ReLU(True),
            nn.Linear(32, 3 * 2)
        )

    def stn(self, x):
        xs = self.localization(x)
        xs = xs.view(-1, 10 * 3 * 3)
        theta = self.fc_loc(xs)
        theta = theta.view(-1, 2, 3)

        grid = F.affine_grid(theta, x.size())
        x = F.grid_sample(x, grid)

        return x

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

        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        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().to(device)

optimizer = optim.SGD(model.parameters(), lr=0.01)

def train(epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)

        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % 500 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100 * batch_idx * len(data) / len(train_loader.dataset), loss.item()))

def test():
    with torch.no_grad():
        model.eval()
        test_loss = 0
        correct = 0
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)

            test_loss += F.nll_loss(output, target, size_average=False).item()
            pred = output.max(1, keepdim=True)[1]
            correct += pred.eq(target.view_as(pred)).sum().item()

        test_loss /= len(test_loader.dataset)

        print('\nTest set: Acerage loss: {:.4f}, Accuracy: {}/{} ({:.0f})%\n'.format(
            test_loss, correct, len(test_loader.dataset), 100 * correct / len(test_loader.dataset)
        ))

def convert_image_np(inp):
            inp = inp.numpy().transpose((1, 2, 0))
            mean = np.array([0.485, 0.456, 0.406])
            std = np.array([0.229, 0.224, 0.225])
            inp = std * inp + mean
            inp = np.clip(inp, 0, 1)
            return inp

def visualize_stn():
    with torch.no_grad():
        data = next(iter(test_loader))[0].to(device)

        input_tensor = data.cpu()
        transformed_input_tensor = model.stn(data).cpu()

        in_grid = convert_image_np(torchvision.utils.make_grid(input_tensor))

        out_grid = convert_image_np(torchvision.utils.make_grid(transformed_input_tensor))

        f, axarr = plt.subplots(1, 2)
        axarr[0].imshow(in_grid)
        axarr[0].set_title('Dataset Images')

        axarr[1].imshow(out_grid)
        axarr[1].set_title('Transformed Images')

for epoch in range(1, 20 + 1):
    train(epoch)
    test()

visualize_stn()

plt.ioff()
plt.show()

训练结果如下：

经过20个Epoch之后，准确率在98%

STN结果可视化：