Task3：Pytorch构建简易CNN字符识别模型

一、前言

在上一节中我们将Datasets封装成DataLoder，可以完成数据集的读取，实际训练过程还需要构建一个CNN模型，通过fetch数据的方式，来训练出我们所期望的模型参数，从而完成字符识别的任务！

二、Pytorch构建简易CNN模型

import torch
torch.manual_seed(0)
torch.backends.cudnn.deterministic = False
torch.backends.cudnn.benchmark = True

import torchvision.models as models
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.autograd import Variable
from torch.utils.data.dataset import Dataset

# 定义模型
class SVHN_Model1(nn.Module):
	def __init__(self):
		super(SVHN_Model1, self).__init__()
		
		# CNN提取特征模块
		self.cnn = nn.Sequential(   # 序列化模型结构
			nn.Conv2d(3, 16, kernel_size=(3, 3), stride=(2, 2)),
			nn.ReLU(), 
			nn.MaxPool2d(2),
			nn.Conv2d(16, 32, kernel_size=(3, 3), stride=(2, 2)),
			nn.ReLU(),
			nn.MaxPool2d(2),
			)
			# 定义全连接层
			self.fc1 = nn.Linear(32*3*7, 11)
			self.fc2 = nn.Linear(32*3*7, 11)
			self.fc3 = nn.Linear(32*3*7, 11)
			self.fc4 = nn.Linear(32*3*7, 11)
			self.fc5 = nn.Linear(32*3*7, 11)
			self.fc6 = nn.Linear(32*3*7, 11)

			def forward(self, img):        
		        feat = self.cnn(img)
		        feat = feat.view(feat.shape[0], -1)
		        c1 = self.fc1(feat)
		        c2 = self.fc2(feat)
		        c3 = self.fc3(feat)
		        c4 = self.fc4(feat)
		        c5 = self.fc5(feat)
		        c6 = self.fc6(feat)
		        return c1, c2, c3, c4, c5, c6

model = SVHN_Model1()

训练模型：

# 损失函数
criterion = nn.CrossEntropyLoss()

# 优化器
optimizer = torch.optim.Adam(model.parameters(), 0.005)

loss_plot, c0_plot = [], []

# 迭代10个Epoch
for epoch in range(10):
	for data in train_loader:
		c0, c1, c2, c3, c4, c5 = model(data[0])
		loss = criterion(c0, data[1][:, 0]) + 
				criterion(c1, data[1][:, 1]) + 
				criterion(c2, data[1][:, 2]) + 
				criterion(c3, data[1][:, 3]) + 
				criterion(c4, data[1][:, 4]) + 
				criterion(c5, data[1][:, 5])

		loss /= 6
		optimizer.zero_grad()
		loss.backward()
		optimizer.step()
		
		loss_plot.append(loss.item())
		c0_plot.append((c0.argmax(1) == data[1][:, 0]).sum().item()*1.0 / c0.shape[0])

	print(epoch)

通过loss_plot、c0_plot绘制变化曲线可以看到训练过程中的损失和准确率变化，一般是随着Epoch的增加，字符识别的准确率逐渐提高！

在Pytorch上可以很方便的使用很多其他数据集上的与训练模型，我们使用ImageNet数据集预训练模型的方式是：

class SVHN_Model2(nn.Module):
	def __init__(self):
		super(SVHN_Model1, self).__init__()
		
		# 下面在序列化产生CNN模型之前，首先加载resnet18的预训练模型，
		model_conv = models.resnet18(pretrained=True)
		model_conv.avgpool = nn.AdaptiveAvgPool2d(1)
		model_conv = nn.Sequential(*list(model_conv.children())[:-1])
		self.cnn = model_conv
		
		self.fc1 = nn.Linear(512, 11)
		self.fc2 = nn.Linear(512, 11)
		self.fc3 = nn.Linear(512, 11)
		self.fc4 = nn.Linear(512, 11)
		self.fc5 = nn.Linear(512, 11)

	def forward(self, img):
		feat = self.cnn(img)
		# print(feat.shape)
		feat = feat.view(feat.shape[0], -1)
		c1 = self.fc1(feat)
		c2 = self.fc2(feat)
		c3 = self.fc3(feat)
		c4 = self.fc4(feat)
		c5 = self.fc5(feat)
		return c1, c2, c3, c4, c5

通过以上的代码就使用Pytorch构建了一个简易的CNN序列化模型来完成字符分类任务，实际上，我们也能通过添加不同预训练模型参数或者调整前馈传播的方式，更改模型，以达到提高识别准确率的目的。