第P5周：运动鞋识别

  >- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/xLjALoOD8HPZcH563En8bQ) 中的学习记录博客**
>- **🍦 参考文章：365天深度学习训练营-第5周：运动鞋品牌识别（训练营内部成员可读）**
>- **🍖 原作者：[K同学啊](https://mp.weixin.qq.com/s/xLjALoOD8HPZcH563En8bQ)**

---

一、前期准备

1.设置GPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
 
import os,PIL,pathlib
 
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
device
device(type='cuda')

 

 2.导入数据 

import random
data_dir = './data/p5_data/train/'
data_dir = pathlib.Path(data_dir)

data_paths = list(data_dir.glob('*'))
classNames = [str(path).split('\\')[3] for path in data_paths]
classNames

 

train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),
    transforms.ToTensor(),
    transforms.Normalize(
    mean = [0.485, 0.456, 0.406],
    std = [0.229, 0.224, 0.225])
])

test_transforms = transforms.Compose([
    transforms.Resize([224,224]),
    transforms.ToTensor(),
    transforms.Normalize(
    mean = [0.485, 0.456, 0.406],
    std = [0.229, 0.224, 0.225])
])

train_dataset = datasets.ImageFolder("./data/p5_data/train/", transform = train_transforms)
test_dataset = datasets.ImageFolder("./data/p5_data/test/", transform = test_transforms)

train_dataset.class_to_idx

batch_size = 32

train_dl = torch.utils.data.DataLoader(train_dataset,
                                      batch_size = batch_size,
                                      shuffle = True,
                                      num_workers = 1)

test_dl = torch.utils.data.DataLoader(test_dataset,
                                     batch_size = batch_size,
                                     shuffle = True,
                                     num_workers = 1)

for X, y in test_dl:
    print("Shape of X[N, C, H, W]:", X.shape)
    print("Shape of y:", y.shape, y.dtype)
    break

二、构建简单的CNN模型 

import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Sequential(
        nn.Conv2d(3, 32, kernel_size=3, stride=1,padding=1), # 32*224*224
        nn.BatchNorm2d(32),
        nn.ReLU())
        
        self.conv2 = nn.Sequential(
        nn.Conv2d(32, 32, kernel_size=3, stride=1,padding=1), # 32*224*224
        nn.BatchNorm2d(32),
        nn.ReLU())
        
        self.pool3 = nn.Sequential(nn.MaxPool2d(2)) # 32*112*112
        
        self.conv4 = nn.Sequential(
        nn.Conv2d(32, 64, kernel_size=3,stride=1, padding=1), # 64*112*112
        nn.BatchNorm2d(64),
        nn.ReLU())
        
        self.conv5 = nn.Sequential(
        nn.Conv2d(64, 64, kernel_size=3, stride=1,padding=1),# 64*112*112
        nn.BatchNorm2d(64),
        nn.ReLU())
        
        self.pool6 = nn.Sequential(nn.MaxPool2d(2)) # 64*56*56
        
        self.conv7 = nn.Sequential(
        nn.Conv2d(64, 128, kernel_size=3, stride=1,padding=1), # 128*56*56
        nn.BatchNorm2d(128),
        nn.ReLU())
        
        self.conv8 = nn.Sequential(
        nn.Conv2d(128, 256, kernel_size=3,stride=1, padding=1),# 256*56*56
        nn.BatchNorm2d(256),
        nn.ReLU())
        
        self.pool9 = nn.Sequential(nn.MaxPool2d(2)) # 256*28*28
        
        self.dropout = nn.Sequential(nn.Dropout(0.2))
        
        self.fc = nn.Sequential(nn.Linear(256*28*28, 2))
        
    def forward(self, x):
        
        batch_size = x.size(0)
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.pool3(x)
        x = self.conv4(x)
        x = self.conv5(x)
        x = self.pool6(x)
        x = self.conv7(x)
        x = self.conv8(x)
        x = self.pool9(x)
        x = self.dropout(x)
        x = x.view(batch_size, -1)
        x = self.fc(x)
        
        return(x)
    
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))

model = Model().to(device)
model
        

 三、训练模型

编写训练函数

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

编写测试函数 

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

设置动态学习率 

def adjust_learning_rate(optimizer, epoch, start_lr):
    
    lr = start_lr * (0.92 ** (epoch // 2))
    
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr
        
learn_rate = 1e-4
optimizer = torch.optim.SGD(model.parameters(), lr = learn_rate)

正式训练

loss_fn = nn.CrossEntropyLoss()
epochs = 40

train_loss = []
train_acc = []
test_loss = []
test_acc = []

for epoch in range(epochs):
    #更新学习率（使用自定义学习率使用）
    adjust_learning_rate(optimizer, epoch, learn_rate)
    
    model.train()
    
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
    #scheduler.step()  #更新学习率（调用官方动态学习率接口时使用）
    
    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)
    
    lr = optimizer.state_dict()['param_groups'][0]['lr']
    
    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:2E}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss,
                         epoch_test_acc*100, epoch_test_loss, lr))

print('Done')

四、 结果可视化 

1. Loss与Accuracy图 

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()

 2. 指定图片进行预测

from PIL import Image

classes = list(train_dataset.class_to_idx)

def predict_one_image(image_path, model, transform, classes):
    
    test_img = Image.open(image_path).convert('RGB')
    plt.imshow(test_img)
    
    test_img = transform(test_img)
    
    img = test_img.to(device).unsqueeze(0)
    
    model.eval()
    output = model(img)
    
    _,pred = torch.max(output,1)
    pred_class = classes[pred]
    print(f'预测结果是:{pred_class}')

predict_one_image(image_path='./data/p5_data/test/adidas/10.jpg',
                 model=model,
                 transform=train_transforms,
                 classes=classes)

 五、保存并加载模型  

PATH = './model/p5model.pth'
torch.save(model.state_dict(), PATH)

#将参数加载到model中
model.load_state_dict(torch.load(PATH, map_location=device))