运动鞋识别

🍨 本文为🔗365天深度学习训练营中的学习记录博客
🍦 参考文章：Pytorch实战 | 第P5周：运动鞋识别
🍖 原作者：K同学啊|接辅导、项目定制

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasetsimport os,PIL,pathlibdevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")device

import os,PIL,random,pathlibdata_dir = r'D:\桌面\46-data'
data_dir = pathlib.Path(data_dir)data_paths  = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[3] for path in data_paths]
classeNames

['test', 'train']

# 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863
train_transforms = transforms.Compose([transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸# transforms.RandomHorizontalFlip(), # 随机水平翻转transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])test_transform = transforms.Compose([transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])train_dataset = datasets.ImageFolder(r"D:\桌面\46-data\train",transform=train_transforms)
test_dataset  = datasets.ImageFolder(r"D:\桌面\46-data\test",transform=train_transforms)

train_dataset.class_to_idx

{'adidas': 0, 'nike': 1}

batch_size = 32train_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

Shape of X [N, C, H, W]:  torch.Size([32, 3, 224, 224])
Shape of y:  torch.Size([32]) torch.int64

import torch.nn.functional as Fclass Model(nn.Module):def __init__(self):super(Model, self).__init__()self.conv1=nn.Sequential(nn.Conv2d(3, 12, kernel_size=5, padding=0), # 12*220*220nn.BatchNorm2d(12),nn.ReLU())self.conv2=nn.Sequential(nn.Conv2d(12, 12, kernel_size=5, padding=0), # 12*216*216nn.BatchNorm2d(12),nn.ReLU())self.pool3=nn.Sequential(nn.MaxPool2d(2))                              # 12*108*108self.conv4=nn.Sequential(nn.Conv2d(12, 24, kernel_size=5, padding=0), # 24*104*104nn.BatchNorm2d(24),nn.ReLU())self.conv5=nn.Sequential(nn.Conv2d(24, 24, kernel_size=5, padding=0), # 24*100*100nn.BatchNorm2d(24),nn.ReLU())self.pool6=nn.Sequential(nn.MaxPool2d(2))                              # 24*50*50self.dropout = nn.Sequential(nn.Dropout(0.2))self.fc=nn.Sequential(nn.Linear(24*50*50, len(classeNames)))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*50x = self.fc(x)return xdevice = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))model = Model().to(device)
model

Using cuda deviceModel((conv1): Sequential((0): Conv2d(3, 12, kernel_size=(5, 5), stride=(1, 1))(1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU())(conv2): Sequential((0): Conv2d(12, 12, kernel_size=(5, 5), stride=(1, 1))(1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU())(pool3): Sequential((0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False))(conv4): Sequential((0): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))(1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU())(conv5): Sequential((0): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1))(1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU())(pool6): Sequential((0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False))(dropout): Sequential((0): Dropout(p=0.2, inplace=False))(fc): Sequential((0): Linear(in_features=60000, out_features=2, bias=True))
)

# 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losstrain_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc  /= sizetrain_loss /= num_batchesreturn 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losstarget_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  /= sizetest_loss /= num_batchesreturn test_acc, test_loss


learn_rate = 1e-4 # 初始学习率
# 调用官方动态学习率接口时使用
lambda1 = lambda epoch: 0.92 ** (epoch // 2)
optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda1) #选定调整方法

loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
epochs     = 40train_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')

Epoch: 1, Train_acc:53.2%, Train_loss:0.767, Test_acc:53.9%, Test_loss:0.675, Lr:1.00E-04
Epoch: 2, Train_acc:61.4%, Train_loss:0.660, Test_acc:60.5%, Test_loss:0.632, Lr:9.20E-05
Epoch: 3, Train_acc:70.5%, Train_loss:0.600, Test_acc:72.4%, Test_loss:0.570, Lr:9.20E-05
Epoch: 4, Train_acc:70.3%, Train_loss:0.582, Test_acc:71.1%, Test_loss:0.545, Lr:8.46E-05
Epoch: 5, Train_acc:71.9%, Train_loss:0.557, Test_acc:69.7%, Test_loss:0.541, Lr:8.46E-05
Epoch: 6, Train_acc:76.1%, Train_loss:0.529, Test_acc:72.4%, Test_loss:0.526, Lr:7.79E-05
Epoch: 7, Train_acc:75.5%, Train_loss:0.488, Test_acc:73.7%, Test_loss:0.484, Lr:7.79E-05
Epoch: 8, Train_acc:78.3%, Train_loss:0.493, Test_acc:75.0%, Test_loss:0.509, Lr:7.16E-05
Epoch: 9, Train_acc:79.1%, Train_loss:0.454, Test_acc:75.0%, Test_loss:0.511, Lr:7.16E-05
Epoch:10, Train_acc:84.5%, Train_loss:0.428, Test_acc:75.0%, Test_loss:0.507, Lr:6.59E-05
Epoch:11, Train_acc:82.7%, Train_loss:0.433, Test_acc:76.3%, Test_loss:0.451, Lr:6.59E-05
Epoch:12, Train_acc:86.5%, Train_loss:0.397, Test_acc:75.0%, Test_loss:0.484, Lr:6.06E-05
Epoch:13, Train_acc:85.9%, Train_loss:0.404, Test_acc:76.3%, Test_loss:0.434, Lr:6.06E-05
Epoch:14, Train_acc:88.8%, Train_loss:0.375, Test_acc:76.3%, Test_loss:0.524, Lr:5.58E-05
Epoch:15, Train_acc:88.4%, Train_loss:0.376, Test_acc:78.9%, Test_loss:0.456, Lr:5.58E-05
Epoch:16, Train_acc:89.0%, Train_loss:0.366, Test_acc:76.3%, Test_loss:0.469, Lr:5.13E-05
Epoch:17, Train_acc:87.8%, Train_loss:0.369, Test_acc:76.3%, Test_loss:0.492, Lr:5.13E-05
Epoch:18, Train_acc:89.0%, Train_loss:0.348, Test_acc:75.0%, Test_loss:0.436, Lr:4.72E-05
Epoch:19, Train_acc:90.6%, Train_loss:0.331, Test_acc:75.0%, Test_loss:0.461, Lr:4.72E-05
Epoch:20, Train_acc:89.8%, Train_loss:0.340, Test_acc:75.0%, Test_loss:0.463, Lr:4.34E-05
Epoch:21, Train_acc:93.0%, Train_loss:0.318, Test_acc:76.3%, Test_loss:0.440, Lr:4.34E-05
Epoch:22, Train_acc:92.0%, Train_loss:0.314, Test_acc:77.6%, Test_loss:0.462, Lr:4.00E-05
Epoch:23, Train_acc:89.8%, Train_loss:0.321, Test_acc:77.6%, Test_loss:0.422, Lr:4.00E-05
Epoch:24, Train_acc:92.6%, Train_loss:0.313, Test_acc:77.6%, Test_loss:0.459, Lr:3.68E-05
Epoch:25, Train_acc:92.2%, Train_loss:0.310, Test_acc:77.6%, Test_loss:0.427, Lr:3.68E-05
Epoch:26, Train_acc:91.8%, Train_loss:0.305, Test_acc:76.3%, Test_loss:0.409, Lr:3.38E-05
Epoch:27, Train_acc:93.2%, Train_loss:0.304, Test_acc:77.6%, Test_loss:0.436, Lr:3.38E-05
Epoch:28, Train_acc:91.8%, Train_loss:0.310, Test_acc:78.9%, Test_loss:0.445, Lr:3.11E-05
Epoch:29, Train_acc:92.4%, Train_loss:0.300, Test_acc:77.6%, Test_loss:0.426, Lr:3.11E-05
Epoch:30, Train_acc:94.2%, Train_loss:0.285, Test_acc:76.3%, Test_loss:0.423, Lr:2.86E-05
Epoch:31, Train_acc:92.2%, Train_loss:0.285, Test_acc:77.6%, Test_loss:0.419, Lr:2.86E-05
Epoch:32, Train_acc:93.8%, Train_loss:0.284, Test_acc:77.6%, Test_loss:0.401, Lr:2.63E-05
Epoch:33, Train_acc:92.6%, Train_loss:0.287, Test_acc:77.6%, Test_loss:0.390, Lr:2.63E-05
Epoch:34, Train_acc:94.6%, Train_loss:0.267, Test_acc:76.3%, Test_loss:0.423, Lr:2.42E-05
Epoch:35, Train_acc:94.2%, Train_loss:0.269, Test_acc:76.3%, Test_loss:0.437, Lr:2.42E-05
Epoch:36, Train_acc:93.6%, Train_loss:0.268, Test_acc:77.6%, Test_loss:0.425, Lr:2.23E-05
Epoch:37, Train_acc:94.2%, Train_loss:0.275, Test_acc:76.3%, Test_loss:0.414, Lr:2.23E-05
Epoch:38, Train_acc:94.6%, Train_loss:0.267, Test_acc:76.3%, Test_loss:0.404, Lr:2.05E-05
Epoch:39, Train_acc:95.4%, Train_loss:0.256, Test_acc:78.9%, Test_loss:0.411, Lr:2.05E-05
Epoch:40, Train_acc:94.2%, Train_loss:0.270, Test_acc:78.9%, Test_loss:0.419, Lr:1.89E-05
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()

在这里插入图片描述

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)  # 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=r"D:\桌面\46-data\train\adidas\1 (3).jpg", model=model, transform=train_transforms, classes=classes)

预测结果是：adidas

# 模型保存
PATH = './model.pth'  # 保存的参数文件名
torch.save(model.state_dict(), PATH)# 将参数加载到model当中
model.load_state_dict(torch.load(PATH, map_location=device))
model

Model((conv1): Sequential((0): Conv2d(3, 12, kernel_size=(5, 5), stride=(1, 1))(1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU())(conv2): Sequential((0): Conv2d(12, 12, kernel_size=(5, 5), stride=(1, 1))(1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU())(pool3): Sequential((0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False))(conv4): Sequential((0): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))(1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU())(conv5): Sequential((0): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1))(1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU())(pool6): Sequential((0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False))(dropout): Sequential((0): Dropout(p=0.2, inplace=False))(fc): Sequential((0): Linear(in_features=60000, out_features=2, bias=True))
)