计算机视觉-街景符号识别3构建模型

import os, sys, glob, shutil, json
import cv2

from PIL import Image
import numpy as np

import torch
from torch.utils.data.dataset import Dataset
import torchvision.transforms as transforms

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)
        
        # 原始SVHN中类别10为数字0
        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)

train_path = glob.glob('./mchar_train/*.png')
train_path.sort()
train_json = json.load(open('train.json'))
train_label = [train_json[x]['label'] for x in train_json]

train_loader = torch.utils.data.DataLoader(
        SVHNDataset(train_path, train_label,
                   transforms.Compose([
                       transforms.Resize((64, 128)),
                       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=10, # 每批样本个数
    shuffle=False, # 是否打乱顺序
    num_workers=0, # 读取的线程个数
)

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(
            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()
device=torch.device("cuda")#设置GPU
# 损失函数
criterion = nn.CrossEntropyLoss()
criterion = criterion.to(device)#损失函数在GPU上运行
model= model.to(device)#模型放在GPU上
# 优化器
optimizer = torch.optim.Adam(model.parameters(), 0.005)
optimizer
loss_plot, c0_plot = [], []
# 迭代10个Epoch
for epoch in range(10):
    for data in train_loader:
        img,target=data
        img=img.to(device)#输入图片放在GPU上
        target=target.to(device)#输入的标签放在GPU上
        c0, c1, c2, c3, c4, c5 = model(img)
        loss = criterion(c0, target[:, 0].long()) + \
                criterion(c1, target[:, 1].long()) + \
                criterion(c2, target[:, 2].long()) + \
                criterion(c3, target[:, 3].long()) + \
                criterion(c4, target[:, 4].long()) 
        loss /= 5
       
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        loss_plot.append(loss.item())
        c0_plot.append((c0.argmax(1) == target[:, 0]).sum().item()*1.0 / c0.shape[0])
        
    print(epoch)

torch.save(model,"moxing")

标签：img,nn,街景,self,torch,train,import,视觉,识别
来源： https://www.cnblogs.com/zhaoyids/p/15835475.html