torch05：CNN--MNIST识别和自己数据集

MachineLP的Github（欢迎follow）：https://github.com/MachineLP

MachineLP的博客目录：小鹏的博客目录

本小节使用torch搭建CNN模型，训练和测试：

（1）定义模型超参数：输出、迭代次数、批量大小、学习率。

（2）定义训练数据，加餐部分是使用自己的数据集：（可参考：https://blog.csdn.net/u014365862/article/details/80506147）

（3）定义模型（定义卷积神经网络）。

（4）定义损失函数，选用适合的损失函数。

（5）定义优化算法（SGD、Adam等）。

（6）保存模型。

---------------------------------我是可爱的分割线---------------------------------

代码部分：

# coding=utf-8
import torch 
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms


# 判定GPU是否存在
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# 定义超参数
num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001

# 手写体数据，（数据+标签）
train_dataset = torchvision.datasets.MNIST(root='./data/',
                                           train=True, 
                                           transform=transforms.ToTensor(),
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='./data/',
                                          train=False, 
                                          transform=transforms.ToTensor())

# # 构建数据管道， 使用自己的数据集请参考：https://blog.csdn.net/u014365862/article/details/80506147 
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size, 
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size, 
                                          shuffle=False)

# 定义自己的卷积神经网络
class ConvNet(nn.Module):
    def __init__(self, num_classes=10):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer3 = nn.Sequential(
            nn.Conv2d(32, 64, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.fc = nn.Linear(3*3*64, num_classes)
        
    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = self.layer3(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

# 定义模型
model = ConvNet(num_classes).to(device)

# 定义损失函数+优化算法
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# 训练模型
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)
        
        # 前向传播+计算loss
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # 后向传播+调整参数
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        # 每100个batch打印一次数据  
        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# 模型测试部分  
# 测试阶段不需要计算梯度，注意 
model.eval()  # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))

# 保存模型参数  
torch.save(model.state_dict(), 'model.ckpt')

加餐：在自己数据集上使用：

其中，train.txt中的数据格式：

gender/0male/0(2).jpg 1
gender/0male/0(3).jpeg 1
gender/0male/0(1).jpg 0

test.txt中的数据格式如下：

gender/0male/0(3).jpeg 1
gender/0male/0(1).jpg 0

gender/1female/1(6).jpg 1

代码部分：

# coding=utf-8
import torch 
import torch.nn as nn
import torchvision
from torch.utils.data import Dataset, DataLoader    
from torchvision import transforms, utils 
from PIL import Image 

# 判定GPU是否存在
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# 定义超参数
num_epochs = 5
num_classes = 10
batch_size = 16
learning_rate = 0.001

def default_loader(path):    
    # 注意要保证每个batch的tensor大小时候一样的。    
    return Image.open(path).convert('RGB')    
    
class MyDataset(Dataset):    
    def __init__(self, txt, transform=None, target_transform=None, loader=default_loader):    
        fh = open(txt, 'r')    
        imgs = []    
        for line in fh:    
            line = line.strip('\n')    
            # line = line.rstrip()    
            words = line.split(' ')    
            imgs.append((words[0],int(words[1])))    
        self.imgs = imgs    
        self.transform = transform    
        self.target_transform = target_transform    
        self.loader = loader    
        
    def __getitem__(self, index):    
        fn, label = self.imgs[index]    
        img = self.loader(fn)    
        if self.transform is not None:    
            img = self.transform(img)    
        return img,label    
        
    def __len__(self):    
        return len(self.imgs)    
    
def get_loader(dataset='train.txt', crop_size=128, image_size=28, batch_size=2, mode='train', num_workers=1):    
    """Build and return a data loader."""    
    transform = []    
    if mode == 'train':    
        transform.append(transforms.RandomHorizontalFlip())    
    transform.append(transforms.CenterCrop(crop_size))    
    transform.append(transforms.Resize(image_size))    
    transform.append(transforms.ToTensor())    
    transform.append(transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)))    
    transform = transforms.Compose(transform)    
    train_data=MyDataset(txt=dataset, transform=transform)    
    data_loader = DataLoader(dataset=train_data,    
                                  batch_size=batch_size,    
                                  shuffle=(mode=='train'),    
                                  num_workers=num_workers)    
    return data_loader    
# 注意要保证每个batch的tensor大小时候一样的。    
# data_loader = DataLoader(train_data, batch_size=2,shuffle=True)    
train_loader = get_loader('train.txt', batch_size=batch_size)    
print(len(train_loader))    
test_loader = get_loader('test.txt', batch_size=batch_size)    
print(len(test_loader))    

# 定义自己的卷积神经网络
class ConvNet(nn.Module):
    def __init__(self, num_classes=10):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(3, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer3 = nn.Sequential(
            nn.Conv2d(32, 64, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.fc = nn.Linear(3*3*64, num_classes)
        
    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = self.layer3(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

# 定义模型
model = ConvNet(num_classes).to(device)

# 定义损失函数+优化算法
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# 训练模型
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)
        
        # 前向传播+计算loss
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # 后向传播+调整参数
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        # 每100个batch打印一次数据  
        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# 模型测试部分  
# 测试阶段不需要计算梯度，注意 
model.eval()  # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))

# 保存模型参数  
torch.save(model.state_dict(), 'model.ckpt')

总结：

本节使用CNN训练MNIST识别、自己数据的识别。

上面加餐部分需要生成自己的txt文件（数据+标签），可以参考这个，自己以前调试用的：https://github.com/MachineLP/py_workSpace/blob/master/g_img_path.py

torch系列：

1. torch01：torch基础

2. torch02：logistic regression--MNIST识别

3. torch03：linear_regression

4. torch04：全连接神经网络--MNIST识别和自己数据集