猫狗识别数据集https://download.csdn.net/download/Victor_Li_/88483483?spm=1001.2014.3001.5501
训练集图片路径
测试集图片路径
训练代码如下
import torch
import torchvision
import matplotlib.pyplot as plt
import torchvision.models as models
import torch.nn as nn
import torch.optim as optim
import torch.multiprocessing as mp
import time
from torch.optim.lr_scheduler import StepLRif __name__ == '__main__':torch.autograd.set_detect_anomaly(True)mp.freeze_support()train_on_gpu = torch.cuda.is_available()if not train_on_gpu:print('CUDA is not available. Training on CPU...')else:print('CUDA is available! Training on GPU...')device = torch.device("cuda" if torch.cuda.is_available() else "cpu")batch_size = 32# 设置数据预处理的转换transform = torchvision.transforms.Compose([torchvision.transforms.Resize((224, 224)), # 调整图像大小为 224x224torchvision.transforms.RandomHorizontalFlip(),torchvision.transforms.RandomRotation(45),torchvision.transforms.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2),torchvision.transforms.ToTensor(), # 转换为张量torchvision.transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]) # 归一化])dataset = torchvision.datasets.ImageFolder('./cats_and_dogs_train',transform=transform)val_ratio = 0.2val_size = int(len(dataset) * val_ratio)train_size = len(dataset) - val_sizetrain_dataset, val_dataset = torch.utils.data.random_split(dataset, [train_size, val_size])train_dataset = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=4,pin_memory=True)val_dataset = torch.utils.data.DataLoader(val_dataset, batch_size=batch_size, num_workers=4, pin_memory=True)# x,y = next(iter(val_dataset))# x = x.permute(1, 2, 0) # 将通道维度调整到最后# x = (x - x.min()) / (x.max() - x.min()) # 反归一化操作# plt.imshow(x) # 将通道维度调整到最后# plt.axis('off') # 关闭坐标轴# plt.show()model = models.resnet34(weights=None)num_classes = 2model.fc = nn.Sequential(nn.Dropout(p=0.2),# nn.BatchNorm4d(model.fc.in_features),nn.Linear(model.fc.in_features, num_classes),nn.Sigmoid(),)lambda_L1 = 0.001lambda_L2 = 0.0001regularization_loss_L1 = 0regularization_loss_L2 = 0for name,param in model.named_parameters():param.requires_grad = Trueif 'bias' not in name:regularization_loss_L1 += torch.norm(param, p=1).detach()regularization_loss_L2 += torch.norm(param, p=2).detach()optimizer = optim.Adam(model.parameters(), lr=0.01)scheduler = StepLR(optimizer, step_size=5, gamma=0.9)criterion = nn.BCELoss().to(device)model.to(device)# print(model)loadfilename = "recognize_cats_and_dogs.pt"savefilename = "recognize_cats_and_dogs3.pt"checkpoint = torch.load(loadfilename)model.load_state_dict(checkpoint['model_state_dict'])def save_checkpoint(epoch, model, optimizer, filename, train_loss=0., val_loss=0.):checkpoint = {'epoch': epoch,'model_state_dict': model.state_dict(),'optimizer_state_dict': optimizer.state_dict(),'train_loss': train_loss,'val_loss': val_loss,}torch.save(checkpoint, filename)num_epochs = 100train_loss = []for epoch in range(num_epochs):running_loss = 0correct = 0total = 0epoch_start_time = time.time()for i, (inputs, labels) in enumerate(train_dataset):# 将数据放到设备上inputs, labels = inputs.to(device), labels.to(device)# 前向计算outputs = model(inputs)one_hot = nn.functional.one_hot(labels, num_classes).float()# 计算损失和梯度loss = criterion(outputs, one_hot) + lambda_L1 * regularization_loss_L1 + lambda_L2 * regularization_loss_L2loss.backward()if ((i + 1) % 2 == 0) or (i + 1 == len(train_dataset)):# 更新模型参数optimizer.step()optimizer.zero_grad()# 记录损失和准确率running_loss += loss.item()train_loss.append(loss.item())_, predicted = torch.max(outputs.data, 1)correct += (predicted == labels).sum().item()total += labels.size(0)accuracy_train = 100 * correct / total# 在测试集上计算准确率with torch.no_grad():running_loss_test = 0correct_test = 0total_test = 0for inputs, labels in val_dataset:inputs, labels = inputs.to(device), labels.to(device)outputs = model(inputs)one_hot = nn.functional.one_hot(labels, num_classes).float()loss = criterion(outputs, one_hot)running_loss_test += loss.item()_, predicted = torch.max(outputs.data, 1)correct_test += (predicted == labels).sum().item()total_test += labels.size(0)accuracy_test = 100 * correct_test / total_test# 输出每个 epoch 的损失和准确率epoch_end_time = time.time()epoch_time = epoch_end_time - epoch_start_timetain_loss = running_loss / len(train_dataset)val_loss = running_loss_test / len(val_dataset)print("Epoch [{}/{}], Time: {:.4f}s, Loss: {:.4f}, Train Accuracy: {:.2f}%, Loss: {:.4f}, Test Accuracy: {:.2f}%".format(epoch + 1, num_epochs, epoch_time, tain_loss,accuracy_train, val_loss, accuracy_test))save_checkpoint(epoch, model, optimizer, savefilename, tain_loss, val_loss)scheduler.step()# plt.plot(train_loss, label='Train Loss')# # 添加图例和标签# plt.legend()# plt.xlabel('Epochs')# plt.ylabel('Loss')# plt.title('Training Loss')## # 显示图形# plt.show()
测试代码如下
import torch
import torchvision
import torch.nn as nn
import torchvision.models as models
import matplotlib.pyplot as plt
import torch.multiprocessing as mpif __name__ == '__main__':mp.freeze_support()train_on_gpu = torch.cuda.is_available()if not train_on_gpu:print('CUDA is not available. Training on CPU...')else:print('CUDA is available! Training on GPU...')device = torch.device("cuda" if torch.cuda.is_available() else "cpu")batch_size = 32transform = torchvision.transforms.Compose([torchvision.transforms.Resize((224,224)), # 调整图像大小为 224x224torchvision.transforms.ToTensor(), # 转换为张量torchvision.transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]) # 归一化])dataset = torchvision.datasets.ImageFolder('./cats_and_dogs_test',transform=transform)test_dataset = torch.utils.data.DataLoader(dataset, batch_size=batch_size, shuffle=True,num_workers=4, pin_memory=True)model = models.resnet34()num_classes = 2for param in model.parameters():param.requires_grad = Falsemodel.fc = nn.Sequential(nn.Dropout(),nn.Linear(model.fc.in_features,num_classes),nn.LogSoftmax(dim=1))model.to(device)# print(model)filename = "recognize_cats_and_dogs.pt"checkpoint = torch.load(filename)model.load_state_dict(checkpoint['model_state_dict'])class_name = ['cat','dog']# 在测试集上计算准确率with torch.no_grad():for inputs, labels in test_dataset:inputs, labels = inputs.to(device), labels.to(device)output = model(inputs)_, predicted = torch.max(output.data, 1)for x,y,z in zip(inputs,labels,predicted):x = (x - x.min()) / (x.max() - x.min())plt.imshow(x.cpu().permute(1,2,0))plt.axis('off')plt.title('predicted: {0}'.format(class_name[z]))plt.show()
部分测试结果如下