• 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
• 🍖 原作者：K同学啊

一 我的环境

电脑：Google Colab

操作系统：Linux

开发工具：jupter Notebook

显卡：NVIDIA A100-SXM4-40GB

开发语言：Python 3.10.12

深度学习环境：Pytorch 2.2.1

cuda：Cuda 12.1

二：开发过程：

1.设置GPU

import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

2.导入数据 & 可视化数据

train_ds = torchvision.datasets.MNIST('data',
                                      train=True,
                                      transform=torchvision.transforms.ToTensor(),
                                      download=True)

test_ds  = torchvision.datasets.MNIST('data',
                                      train=False,
                                      transform=torchvision.transforms.ToTensor(),
                                      download=True)
batch_size = 32

train_dl = torch.utils.data.DataLoader(train_ds,
                                       batch_size=batch_size,
                                       shuffle=True)

test_dl  = torch.utils.data.DataLoader(test_ds,
                                       batch_size=batch_size)
imgs, labels = next(iter(train_dl))
imgs.shape

# Visalization of Dataset
import numpy as np

plt.figure(figsize=(20, 5))
for i, imgs in enumerate(imgs[:20]):
    npimg = np.squeeze(imgs.numpy())
    plt.subplot(2, 10, i+1)
    plt.imshow(npimg, cmap=plt.cm.binary)
    plt.axis('off')

plt.show()

3. 构建CNN网络

# CNN model
import torch.nn.functional as F

num_classes = 10

class Model(nn.Module):
     def __init__(self):
        super().__init__()
        
        # convolutional layer: input is a single-channel image, out_channels = 32 feature maps,kernel size of 3x3
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3)

        # max pooling layer:  reduces the size of the feature maps by half
        self.pool1 = nn.MaxPool2d(2)

        # Second convolutional layer: takes the 32 feature maps as input and produces 64 output feature maps.
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)

        # Second pooling layer, further reduces the size of the feature maps by half.
        self.pool2 = nn.MaxPool2d(2)

        self.fc1 = nn.Linear(1600, 64)
        self.fc2 = nn.Linear(64, num_classes)

     def forward(self, x):
        x = self.pool1(F.relu(self.conv1(x)))
        x = self.pool2(F.relu(self.conv2(x)))

        x = torch.flatten(x, start_dim=1)

        x = F.relu(self.fc1(x))
        x = self.fc2(x)

        return x

三、 训练模型

1. 设置超参数

loss_fn    = nn.CrossEntropyLoss()
learn_rate = 1e-2 
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

2. 训练函数

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  
    num_batches = len(dataloader) 

    train_loss, train_acc = 0, 0  
    
    for X, y in dataloader:  
        X, y = X.to(device), y.to(device)
        
       
        pred = model(X)          
        loss = loss_fn(pred, y)  
        
        
        optimizer.zero_grad()  
        loss.backward()        
        optimizer.step()       
        
        
        train_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()
            
    train_acc  /= size
    train_loss /= num_batches

    return train_acc, train_loss

3. 测试函数

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  
    num_batches = len(dataloader)          
    test_loss, test_acc = 0, 0
    
    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)
            
            target_pred = model(imgs)
            loss        = loss_fn(target_pred, target)
            
            test_loss += loss.item()
            test_acc  += (target_pred.argmax(1) == target).type(torch.float).sum().item()

    test_acc  /= size
    test_loss /= num_batches

    return test_acc, test_loss

4. 训练模型

epochs     = 5
train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []

for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
    
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
    
    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)
    
    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%，Test_loss:{:.3f}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')

5. 可视化结果

import matplotlib.pyplot as plt

import warnings
warnings.filterwarnings("ignore")              
plt.rcParams['font.sans-serif']    = ['SimHei'] 
plt.rcParams['axes.unicode_minus'] = False     
plt.rcParams['figure.dpi']         = 100       

epochs_range = range(epochs)

plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)

plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

四、个人总结

1. 深度学习的理论还是不够扎实, 需要回去继续补齐 CNN架构为什么这么设计, tricks是什么, 要注意什么.