第P5周-Pytorch实现运动鞋品牌识别

• 🍨 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

具体实现

（一）环境

语言环境：Python 3.10
编 译 器: PyCharm
框 架: Pytorch

（二）具体步骤

时间关系，代码很差…

1. utils.py

针对数据文件的目录情况进行了优化

import torch  
import pathlib  
import matplotlib.pyplot as plt  
from torchvision.transforms import transforms  
  
  
# 第一步：设置GPU  
def USE_GPU():  
    if torch.cuda.is_available():  
        print('CUDA is available, will use GPU')  
        device = torch.device("cuda")  
    else:  
        print('CUDA is not available. Will use CPU')  
        device = torch.device("cpu")  
  
    return device  
  
temp_dict = dict()  
def recursive_iterate(path):  
    """  
    根据所提供的路径遍历该路径下的所有子目录，列出所有子目录下的文件  
    :param path: 路径  
    :return: 返回最后一级目录的数据  
    """    path = pathlib.Path(path)  
    for file in path.iterdir():  
        if file.is_file():  
            temp_key = str(file).split('\\')[-2]  
            if temp_key in temp_dict:  
                temp_dict.update({temp_key: temp_dict[temp_key] + 1})  
            else:  
                temp_dict.update({temp_key: 1})  
            # print(file)  
        elif file.is_dir():  
            recursive_iterate(file)  
  
    return temp_dict  
  
  
def data_from_directory(directory, train_dir=None, test_dir=None, show=False):  
    """  
    提供是的数据集是文件形式的，提供目录方式导入数据，简单分析数据并返回数据分类  
    :param test_dir: 是否设置了测试集目录  
    :param train_dir: 是否设置了训练集目录  
    :param directory: 数据集所在目录  
    :param show: 是否需要以柱状图形式显示数据分类情况,默认显示  
    :return: 数据分类列表,类型: list  
    """    global total_image  
    print("数据目录：{}".format(directory))  
    data_dir = pathlib.Path(directory)  
  
    # for d in data_dir.glob('**/*'): # **/*通配符可以遍历所有子目录  
    #     if d.is_dir():  
    #         print(d)    class_name = []  
    total_image = 0  
    temp_sum = 0  
  
    if train_dir is None or test_dir is None:  
        data_path = list(data_dir.glob('*'))  
        class_name = [str(path).split('\\')[-1] for path in data_path]  
        print("数据分类: {}, 类别数量：{}".format(class_name, len(list(data_dir.glob('*')))))  
        total_image = len(list(data_dir.glob('*/*')))  
        print("图片数据总数: {}".format(total_image))  
    else:  
        temp_dict.clear()  
        train_data_path = directory + '/' + train_dir  
        train_data_info = recursive_iterate(train_data_path)  
        print("{}目录:{},{}".format(train_dir, train_data_path, train_data_info))  
  
        temp_dict.clear()  
        test_data_path = directory + '/' + test_dir  
        print("{}目录:{},{}".format(test_dir,  test_data_path, recursive_iterate(test_data_path)))  
        class_name = temp_dict.keys()  
  
    if show:  
        # 隐藏警告  
        import warnings  
        warnings.filterwarnings("ignore")  # 忽略警告信息  
        plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签  
        plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号  
        plt.rcParams['figure.dpi'] = 100  # 分辨率  
  
        for i in class_name:  
            data = len(list(pathlib.Path((directory + '\\' + i + '\\')).glob('*')))  
            plt.title('数据分类情况')  
            plt.grid(ls='--', alpha=0.5)  
            plt.bar(i, data)  
            plt.text(i, data, str(data), ha='center', va='bottom')  
            print("类别-{}:{}".format(i, data))  
            temp_sum += data  
        plt.show()  
  
    if temp_sum == total_image:  
        print("图片数据总数检查一致")  
    else:  
        print("数据数据总数检查不一致，请检查数据集是否正确！")  
    return class_name  
  
  
def get_transforms_setting(size):  
    """  
    获取transforms的初始设置  
    :param size: 图片大小  
    :return: transforms.compose设置  
    """    transform_setting = {  
        'train': transforms.Compose([  
            transforms.Resize(size),  
            transforms.ToTensor(),  
            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])  
        ]),  
        'test': transforms.Compose([  
            transforms.Resize(size),  
            transforms.ToTensor(),  
            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])  
        ])  
    }  
  
    return transform_setting

**2.**model.py

将CNN网络模板写到一个单独文件里，方便调用。

import torch.nn as nn  
import torch
import torch.nn.functional as F

class Model_Shoes(nn.Module):  
    def __init__(self, classNames):  
        super(Model_Shoes, self).__init__()  
        self.conv1 = nn.Sequential(  
            nn.Conv2d(3, 12, kernel_size=5, padding=0),  # 12*220*220  
            nn.BatchNorm2d(12),  
            nn.ReLU())  
  
        self.conv2 = nn.Sequential(  
            nn.Conv2d(12, 12, kernel_size=5, padding=0),  # 12*216*216  
            nn.BatchNorm2d(12),  
            nn.ReLU())  
  
        self.pool3 = nn.Sequential(  
            nn.MaxPool2d(2))  # 12*108*108  
  
        self.conv4 = nn.Sequential(  
            nn.Conv2d(12, 24, kernel_size=5, padding=0),  # 24*104*104  
            nn.BatchNorm2d(24),  
            nn.ReLU())  
  
        self.conv5 = nn.Sequential(  
            nn.Conv2d(24, 24, kernel_size=5, padding=0),  # 24*100*100  
            nn.BatchNorm2d(24),  
            nn.ReLU())  
  
        self.pool6 = nn.Sequential(  
            nn.MaxPool2d(2))  # 24*50*50  
  
        self.dropout = nn.Sequential(  
            nn.Dropout(0.2))  
  
        self.fc = nn.Sequential(  
            nn.Linear(24 * 50 * 50, len(classNames)))  
  
    def forward(self, x):  
        batch_size = x.size(0)  
        x = self.conv1(x)  # 卷积-BN-激活  
        x = self.conv2(x)  # 卷积-BN-激活  
        x = self.pool3(x)  # 池化  
        x = self.conv4(x)  # 卷积-BN-激活  
        x = self.conv5(x)  # 卷积-BN-激活  
        x = self.pool6(x)  # 池化  
        x = self.dropout(x)  
        x = x.view(batch_size, -1)  # flatten 变成全连接网络需要的输入 (batch, 24*50*50) ==> (batch, -1), -1 此处自动算出的是24*50*50  
        x = self.fc(x)  
  
        return x

3. config.py

将训练的相关参数写到config.py中

import argparse  
  
def get_options(parser=argparse.ArgumentParser()):  
    parser.add_argument('--workers', type=int, default=0, help='Number of parallel workers')  
    parser.add_argument('--batch-size', type=int, default=32, help='input batch size, default=32')  
    parser.add_argument('--lr', type=float, default=1e-4, help='learning rate, default=0.0001')  
    parser.add_argument('--epochs', type=int, default=50, help='number of epochs')  
    parser.add_argument('--seed', type=int, default=112, help='random seed')  
    parser.add_argument('--save-path', type=str, default='./models/', help='path to save checkpoints')  
  
    opt = parser.parse_args()  
  
    if opt:  
        print(f'num_workers:{opt.workers}')  
        print(f'batch_size:{opt.batch_size}')  
        print(f'learn rate:{opt.lr}')  
        print(f'epochs:{opt.epochs}')  
        print(f'random seed:{opt.seed}')  
        print(f'save_path:{opt.save_path}')  
  
    return opt  
  
if __name__ == '__main__':  
    opt = get_options()

**4. main.py

from torch import nn  
from torchvision import datasets  
  
from Utils import USE_GPU, data_from_directory, get_transforms_setting  
import torch  
import os, PIL, pathlib  
from model import Model_Shoes  
  
import config  
  
opt = config.get_options()  
print(opt)  
  
device = USE_GPU()  
  
DATA_DIR = "./data/shoes"  
classNames = data_from_directory(DATA_DIR, train_dir="train", test_dir="test")  
print(list(classNames))  
  
transforms_setting = get_transforms_setting([224, 224])  
train_dataset = datasets.ImageFolder(DATA_DIR + "/train", transforms_setting['train'])  
test_dataset = datasets.ImageFolder(DATA_DIR + "/test", transforms_setting['test'])  
print(train_dataset.class_to_idx)  
  
batch_size = opt.batch_size  
train_dl = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)  
test_dl = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=True)  
  
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  
  
  
model = Model_Shoes(classNames).to(device)  
print(model)  
  
# 训练循环  
def train(dataloader, model, loss_fn, optimizer):  
    size = len(dataloader.dataset)  # 训练集的大小  
    num_batches = len(dataloader)  # 批次数目, (size/batch_size，向上取整)  
  
    train_loss, train_acc = 0, 0  # 初始化训练损失和正确率  
  
    for X, y in dataloader:  # 获取图片及其标签  
        X, y = X.to(device), y.to(device)  
  
        # 计算预测误差  
        pred = model(X)  # 网络输出  
        loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失  
  
        # 反向传播  
        optimizer.zero_grad()  # grad属性归零  
        loss.backward()  # 反向传播  
        optimizer.step()  # 每一步自动更新  
  
        # 记录acc与loss  
        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  
  
  
def test(dataloader, model, loss_fn):  
    size = len(dataloader.dataset)  # 测试集的大小  
    num_batches = len(dataloader)  # 批次数目, (size/batch_size，向上取整)  
    test_loss, test_acc = 0, 0  
  
    # 当不进行训练时，停止梯度更新，节省计算内存消耗  
    with torch.no_grad():  
        for imgs, target in dataloader:  
            imgs, target = imgs.to(device), target.to(device)  
  
            # 计算loss  
            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  
  
def adjust_learning_rate(optimizer, epoch, start_lr):  
    # 每 2 个epoch衰减到原来的 0.92    lr = start_lr * (0.92 ** (epoch // 2))  
    for param_group in optimizer.param_groups:  
        param_group['lr'] = lr  
  
learn_rate = opt.lr # 初始学习率  
optimizer  = torch.optim.SGD(model.parameters(), lr=learn_rate)  
  
loss_fn = nn.CrossEntropyLoss()  # 创建损失函数  
epochs = opt.epochs  
  
train_loss = []  
train_acc = []  
test_loss = []  
test_acc = []  
  
for epoch in range(epochs):  
    # 更新学习率（使用自定义学习率时使用）  
    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)  
  
    # 获取当前的学习率  
    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')  
  
import matplotlib.pyplot as plt  
#隐藏警告  
import warnings  
warnings.filterwarnings("ignore")               #忽略警告信息  
plt.rcParams['font.sans-serif']    = ['SimHei'] # 用来正常显示中文标签  
plt.rcParams['axes.unicode_minus'] = False      # 用来正常显示负号  
plt.rcParams['figure.dpi']         = 100        #分辨率  
  
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()  
  
# 模型保存  
MODEL_SAVE_NAME = "cnn-shoes.pth"  
torch.save(model.state_dict(), opt.save_path + MODEL_SAVE_NAME)

**5. 预测指定图片

import torch  
  
from model import Model_Shoes  
from Utils import USE_GPU, get_transforms_setting  
from PIL import Image  
  
from PIL import Image  
  
device = USE_GPU()  
transform_setting = get_transforms_setting([224, 224])  
  
classes = ['adidas', 'nike']  
model = Model_Shoes(classes)  
model.load_state_dict(torch.load('./models/cnn-shoes.pth', map_location=device))  
model.to(device)  
  
def predict_one_image(image_path, model, transform, classes):  
    test_img = Image.open(image_path).convert('RGB')  
    # plt.imshow(test_img)  # 展示预测的图片  
  
    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}')  
  
# 预测训练集中的某张照片  
predict_one_image(image_path='./mydata/shoes/1.png',  
                  model=model,  
                  transform=transform_setting['train'],  
                  classes=classes)

（三）总结

本次学习对于构建CNN网络中的 nn.BatchNorm2d(）做了初步的了解，nn.BatchNorm2d(）进行数据的归一化处理，这使得数据在进行Relu之前不会因为数据过大而导致网络性能的不稳定，BatchNorm2d()函数数学原理如下：

BatchNorm2d()内部的参数如下：

1.num_features：一般输入参数为batch_sizenum_featuresheight*width，即为其中特征的数量

2.eps：分母中添加的一个值，目的是为了计算的稳定性，默认为：1e-5

3.momentum：一个用于运行过程中均值和方差的一个估计参数（我的理解是一个稳定系数，类似于SGD中的momentum的系数）

4.affine：当设为true时，会给定可以学习的系数矩阵gamma和beta
参考链接：https://blog.csdn.net/bigFatCat_Tom/article/details/91619977