pytorch如何利用ResNet18进行手写数字识别_开发_开发者

利用ResNet18进行手写数字识别

先写resnet18.py

代码如下：

import torch
from torch import nn
from torch.nn import functional as F


class ResBlk(nn.Module):
  """
  resnet block
  """

  def __init__(self, ch_in, ch_out, stride=1):
    """

    :param ch_in:
    :param ch_out:
    """
    super(ResBlk, self).__init__()

    self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=stride, padding=1)
    self.bn1 = nn.BATchNorm2d(ch_out)
    self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)
    self.bn2 = nn.BatchNorm2d(ch_out)

    self.extra = nn.Sequential()

    if ch_out != ch_in:
      # [b, ch_in, h, w] => [b, ch_out, h, w]
      self.extra = nn.Sequential(
        nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=stride),
        nn.BatchNorm2d(ch_out)
      )

  def forward(self, x):
    """

    :param x: [b, ch, h, w]
    :return:
    """
    out = F.relu(self.bn1(self.conv1(x)))
    out = self.bn2(self.conv2(out))

    # short cut
    # extra module:[b, ch_in, h, w] => [b, ch_out, h, w]
    # element-wise add:
    out = self.extra(x) + out
    out = F.relu(out)

    return out


class ResNet18(nn.Module):
  def __init__(self):
    super(ResNet18, self).__init__()

    self.conv1 = nn.Sequential(
      nn.Conv2d(1, 64, kernel_size=3, stride=3, padding=0),
      nn.BatchNorm2d(64)
    )
    # followed 4 blocks

    # [b, 64, h, w] => [b, 128, h, w]
    self.blk1 = ResBlk(64, 128, stride=2)

    # [b, 128, h, w] => [b, 256, h, w]
    self.blk2 = ResBlk(128, 256, stride=2)

    # [b, 256, h, w] => [b, 512, h, w]
    self.blk3 = ResBlk(256, 512, stride=2)

    # [b, 512, h, w] => [b, 512, h, w]
    self.blk4 = ResBlk(512, 512, stride=2)

    self.outlayer = nn.Linear(512 * 1 * 1, 10)

  def forward(self, x):
    """

    :param x:
    :return:
    """
    # [b, 1, h, w] => [b, 64, h, w]
    x = F.relu(self.conv1(x))

    # [b, 64, h, w] => [b, 512, h, w]
    x = self.blk1(x)
    x = self.blk2(x)
    x = self.blk3(x)
    x = self.blk4(x)

    # print(x.shape) # [b, 512, 1, 1]
    # 意思就是不管之前的特征图尺寸为多少，只要设置为(1,1)，那么最终特征图大小都为(1,1)
    # [b, 512, h, w] => [b, 512, 1, 1]
    x = F.adaptive_avg_pool2d(x, [1, 1])
    x = x.view(x.size(0), -1)
    x = self.outlayer(x)

    return x


def main():
  blk = ResBlk(1, 128, stride=4)
  tmp = torch.randn(512, 1, 28, 28)
  out = blk(tmp)
  print('blk', out.shape)

  model = ResNet18()
  x = torch.randn(512, 1, 28, 28)
  out = model(x)
  print('resnet', out.shape)
  print(model)


if __name__ == '__main__':
  main()

再写绘图utils.py

代码如下

import torch
from matplotlib import pyplot as plt

device = torch.device('cuda')


def plot_curve(data):
  fig = plt.figure()
  plt.plot(range(len(data)), data, color='blue')
  plt.legend(['value'], loc='upper right')
  plt.xlabel('step')
  plt.ylabel('value')
  plt.show()


def plot_image(img, label, name):
  fig = plt.figure()
  for i in range(6):
    plt.subplot(2, 3, i + 1)
    plt.tight_layout()
    plt.imshow(img[i][0] * 0.3081 + 0.1307, cmap='gray', interpolation='none')
    plt.title("{}: {}".format(name, label[i]python.item()))
    plt.xticks([])
    plt.yticks([])
  plt.show()


def one_hot(label, depth=10):
  out = torch.zeros(label.size(0), depth).cuda()
  idx = label.view(-1, 1)
  out.scatter_(dim=1, index=idx, value=1)
  return out

最后是主函数mnist_train.py

代码如下：

import torch
from torch import nn
from torch.nn import functional as F
from torch import optim
from resnet18 import ResNet18

import torchvision
from matplotlib import pyplot as plt

from utils import plot_image, plot_curve, one_hot

batch_size = 512

# 加载数据
train_loader = torch.utils.data.DataLoader(
  torchvision.datasets.MNIST('mnist_data', train=True, download=True,
               transform=torchvision.transforms.Compose([
                 torchvision.transforms.ToTensor(),
                 torchvision.transforms.Normalize(
                   (0.1307,), (0.3081,))
               ])),
  batch_size=batch_size, shuffle=True)

test_loader = torch.utils.data.DataLoader(
  torchvision.datasets.MNIST('mnist_data/', train=False, download=True,
               transform=torchvision.transforms.Coandroidmpose([
                 torchvision.transforms.ToTensor(),
                 torchvision.transforms.Normalize(
                   (0.1307,), (0.3081,))
               ])),
  batch_size=batch_size, shuffle=False)

# 在装载完成后，我们可以选取其编程客栈中一个批次的数据进行预览
x, y = next(iter(train_loader))

# x:[512, 1, 28, 28], y:[512]
print(x.shape, y.shape, x.min(), x.max())
plot_image(x, y, 'image sample')

device = torch.device('cuda')

net = ResNet18().to(device)

optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9)

train_loss = []

for epoch in range(5):

  # 训练
  net.train()
  for batch_idx, (x, y) in enumerate(train_loader):

    # x: [b, 1, 28, 28], y: [512]
    # [b, 1, 28, 28] => [b, 10]
    x, y = x.to(device), y.to(device)
    out = net(x)
    # [b, 10]
    y_onehot = one_hot(y)
    # loss = mse(out, y_onehot)
    loss = F.mse_loss(out, y_onehot).开发者_Python教程to(device)
    # 先给梯度清0
    optimizer.zero_grad()
    loss.backward()
    # w' = w - lr*grad
    optimizer.step()

    train_loss.append(loss.item())

    if batch_idx % 10 == 0:
      print(epoch, batch_idx, loss.item())

plot_curve(train_loss)编程客栈
# we get optimal [w1, b1, w2, b2, w3, b3]

# 测试
net.eval()
total_correct = 0
for x, y in test_loader:
  x, y = x.cuda(), y.cuda()
  out = net(x)
  # out: [b, 10] => pred: [b]
  pred = out.argmax(dim=1)
  correct = pred.eq(y).sum().float().item()
  total_correct += correct

total_num = len(test_loader.dataset)
acc = total_correct / total_num
print('test acc:', acc)

x, y = next(iter(test_loader))
x, y = x.cuda(), y.cuda()
out = net(x)
pred = out.argmax(dim=1)
x = x.cpu()
pred = pred.cpu()
plot_image(x, pred, 'test')

结果为：