Pytorch学习笔记（十九）Image and Video - Spatial Transformer Networks Tutorial

这篇博客瞄准的是 pytorch 官方教程中 Image and Video 章节的 Spatial Transformer Networks Tutorial 部分。

• 官网链接：https://pytorch.org/tutorials/intermediate/spatial_transformer_tutorial.html

完整网盘链接: https://pan.baidu.com/s/1L9PVZ-KRDGVER-AJnXOvlQ?pwd=aa2m 提取码: aa2m 

---

Spatial Transformer Networks Tutorial

在本教程将介绍如何使用 Spatial Transformer Network 的视觉注意机制来增强模型。可以在 DeepMind 论文 中信息。

Spatial Transformer Network, STN 是对任何可微空间注意力概括，允许神经网络学习如何对输入图像进行空间变换，以增强模型的几何不变性，例如裁剪ROI区域、缩放、校正图像的方向。

STN 的最大优点之一是只需进行很少的改动就可以将其插入任何现有的 CNN 中。

导入必要的包

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()

---

Loading the data

from six.moves import urllib
opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
urllib.request.install_opener(opener)

计算加速设备

device = torch.accelerator.current_accelerator().type if torch.accelerator.is_available() else 'cpu'

数据集加载器

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

---

Depicting spatial transformer networks

STN 由三个主要组成部分：

• 定位网络是一个常规的 CNN，负责将转换的参数进行回归。这部分的模型参数（即模型所拥有的转换能力）不从当前数据集中训练得到，而是从整体模型中以提高全局准确性的训练目标上学习；
• 网格生成器将输入图像中每个像素对应到输出图像中的网格上；
• 采样器使用变换参数并将其作用在输入图像上；

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)
        
        # 定位模块
        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)
        )
        
        # 回归模块
        self.fc_loc = nn.Sequential(
            nn.Linear(10 * 3 * 3, 32),
            nn.ReLU(True),
            nn.Linear(32, 3*2)
        )
        
        # 初始化权重
        self.fc_loc[2].weight.data.zero_()
        self.fc_loc[2].bias.data.copy_(torch.tensor([1, 0, 0, 0, 1, 0], dtype=torch.float))
        
    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)

创建模型

model = Net().to(device)

---

Training the model

模型整体以监督的方式学习分类任务。同时以端到端的方式自动学习 STN 部分。

定义训练函数

def train(epochs):
    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(train_loader), loss.item()))

定义测试函数

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

---

Visualizing the STN results

定义一个辅助函数来查看 STN 的训练结果。

将图像转为numpy数组：

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

可视化stn

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')

训练

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

可视化

visualize_stn()
plt.ioff()
plt.show()