Datawhale 零基础入门CV-Task3 字符识别模型
3 字符识别模型
本章接续前两章内容,对街景字符编码识别赛题的简单理解。在前两章中进行了赛题的背景知识了解和赛题数据的读取。本章主要就是搭建出一个字符识别模型,以及对CNN的学习。
3.1 目标
- 了解并学习CNN的基础原理
- 使用Pytorch框架搭建CNN模型,完成训练
3.2 CNN
卷积神经网络是一种前馈性神经网络,也是深度学习中的一种比较有代表的一种算法。随着深度学习理论的提出和数值计算设备的改进,卷及神经网络得到了快速地发展,目前已在许多方面得到广泛的应用。例如:图像分类,图像检索,物体检测和语义分割等方面。
CNN每一层由众多卷积核组成,每个卷积核对输入的像素进行卷积操作,得到下一次的输入。随着网络层的增加,卷积核会逐渐扩大感受视野,并缩减图像的尺寸。
CNN是一种层次模型,输入原始数据。通过卷积、池化、非线性激活函数和全连接层构成。如下图:
-
前世今生
-
LeNet-5(1998)
-
AlexNet(2012)
-
VGG-16(2014)
-
Inception-v1(2014)
- ResNet-50(2015)
3.3 Pytorch搭建CNN模型
本章构建字符识别模型,完成字符识别功能。
- 包含两个卷积层,并联6个全连接层进行分类。
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
<div STYLE="page-break-after: always;"></div>
# 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(
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),
)
#
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()
- 训练代码:
<div STYLE="page-break-after: always;"></div>
# 损失函数
criterion = nn.CrossEntropyLoss()
<div STYLE="page-break-after: always;"></div>
# 优化器
optimizer = torch.optim.Adam(model.parameters(), 0.005)
loss_plot, c0_plot = [], []
<div STYLE="page-break-after: always;"></div>
# 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)
- 为了提高精度,在ImageNet数据集上的预测训练模型
class SVHN_Model2(nn.Module):
def __init__(self):
super(SVHN_Model1, self).__init__()
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
3.4 小结
- CNN前世今生以及构建的简易识别模型。