零基础入门CV之街道字符识别 Task3 字符识别模型

深度学习与神经网络

此前没有深度学习神经网络的基础,理解CNN比较困难,于是先观看了B站上吴恩达深度学习课程,从logistics回归学起,到单层神经网络,多层神经网络,基本弄懂了损失函数,成本函数,梯度下降法,激活函数,正向传播和反向传播,超参数,收敛,迭代等概念。

CNN

配合该博文理解CNN->通俗理解卷积神经网络

卷积神经网络(简称CNN)是一类特殊的人工神经网络,是深度学习中重要的一个分支。CNN在很多领域都表现优异,精度和速度比传统计算学习算法高很多。特别是在计算机视觉领域,CNN是解决图像分类、图像检索、物体检测和语义分割的主流模型。

CNN每一层由众多的卷积核组成,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野,并缩减图像的尺寸。

CNN是一种层次模型,输入的是原始的像素数据。CNN通过卷积(convolution)、池化(pooling)、非线性激活函数(non-linear activation function)和全连接层(fully connected layer)构成。

通过多次卷积和池化,CNN的最后一层将输入的图像像素映射为具体的输出。如在分类任务中会转换为不同类别的概率输出,然后计算真实标签与CNN模型的预测结果的差异,并通过反向传播更新每层的参数,并在更新完成后再次前向传播,如此反复直到训练完成 。

与传统机器学习模型相比,CNN具有一种端到端(End to End)的思路。在CNN训练的过程中是直接从图像像素到最终的输出,并不涉及到具体的特征提取和构建模型的过程,也不需要人工的参与。

pytorch构建CNN模型

import os, sys, glob, shutil, json

os.environ["CUDA_VISIBLE_DEVICES"] = '0'
import cv2
from PIL import Image
import numpy as np
from tqdm import tqdm, tqdm_notebook
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

#步骤1:定义好读取图像的Dataset
class SVHNDataset(Dataset):
    def __init__(self, img_path, img_label, transform=None):
        self.img_path = img_path

        self.img_label = img_label
        if transform is not None:
            self.transform = transform
        else:
            self.transform = None

    def __getitem__(self, index):
        img = Image.open(self.img_path[index]).convert('RGB')

        if self.transform is not None:
            img = self.transform(img)

        # 设置最⻓的字符⻓度为5个
        lbl = np.array(self.img_label[index], dtype=np.int)
        lbl = list(lbl) + (5 - len(lbl)) * [10]
        return img, torch.from_numpy(np.array(lbl[:5]))

    def __len__(self):
        return len(self.img_path)


##步骤2:定义好训练数据和验证数据的Dataset
train_path = glob.glob('../input/train/*.png')
train_path.sort()
train_json = json.load(open('../input/train.json'))
train_label = [train_json[x]['label'] for x in train_json]
print(len(train_path), len(train_label))
train_loader = torch.utils.data.DataLoader(
    SVHNDataset(train_path, train_label,
                transforms.Compose([
                    transforms.Resize((64, 128)),
                    transforms.RandomCrop((60, 120)),
                    transforms.ColorJitter(0.3, 0.3, 0.2),
                    transforms.RandomRotation(5),
                    transforms.ToTensor(),
                    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
                ])),
    batch_size=40,
    shuffle=True,
    num_workers=0,
)
val_path = glob.glob('../input/val/*.png')
val_path.sort()
val_json = json.load(open('../input/val.json'))
val_label = [val_json[x]['label'] for x in val_json]
print(len(val_path), len(val_label))
val_loader = torch.utils.data.DataLoader(
    SVHNDataset(val_path, val_label,
                transforms.Compose([
                    transforms.Resize((60, 120)),
                    # transforms.ColorJitter(0.3, 0.3, 0.2),
                    # transforms.RandomRotation(5),
                    transforms.ToTensor(),
                    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
                ])),
    batch_size=40,
    shuffle=False,
    num_workers=0,
)
# 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()

# 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(2):
    for data in train_loader:
        c0, c1, c2, c3, c4, c5 = model(data[0])
        data[1] = data[1].long()
        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()

       # if i % 100 == 0:
        print(loss)

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

    print(epoch)

零基础入门CV之街道字符识别 Task3 字符识别模型_第1张图片

你可能感兴趣的:(CV)