20 鱼币
请根据以下多标签分类ResNet网络模型和DenseNet网络模型分别修改提供的训练代码train.py，预测代码predict.py和测试代码evaluate.py，以分别适应两个网络模型 ResNet网络模型代码如下： import torch import torch.nn as nn import torch.nn.functional as F # ResNet网络架构 class BasicBlock(nn.Module): expansion = 1 def __init__(self, in_planes, planes, stride=1): super(BasicBlock, self).__init__() self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn1 = nn.BatchNorm2d(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False) self.bn2 = nn.BatchNorm2d(planes) self.shortcut = nn.Sequential() if stride != 1 or in_planes != self.expansion*planes: self.shortcut = nn.Sequential( nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(self.expansion*planes) ) def forward(self, x): out = F.relu(self.bn1(self.conv1(x))) out = self.bn2(self.conv2(out)) out += self.shortcut(x) out = F.relu(out) return out class ResNet(nn.Module): def __init__(self, block, num_blocks, num_classes): super(ResNet, self).__init__() self.in_planes = 64 self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False) self.bn1 = nn.BatchNorm2d(64) self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1) self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2) self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2) self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2) self.linear = nn.Linear(512*block.expansion, num_classes) def _make_layer(self, block, planes, num_blocks, stride): strides = [stride] + [1]*(num_blocks-1) layers = [] for stride in strides: layers.append(block(self.in_planes, planes, stride)) self.in_planes = planes * block.expansion return nn.Sequential(*layers) def forward(self, x): out = F.relu(self.bn1(self.conv1(x))) out = self.layer1(out) out = self.layer2(out) out = self.layer3(out) out = self.layer4(out) out = F.avg_pool2d(out, 4) out = out.view(out.size(0), -1) out = self.linear(out) out = torch.sigmoid(out) return out def ResNet18(num_classes): return ResNet(BasicBlock, [2,2,2,2], num_classes) 复制代码 DenseNet网络模型代码如下： import torch import torch.nn as nn import torch.nn.functional as F # DenseNet网络架构 class BasicBlock(nn.Module): def __init__(self, inplanes, outplanes): super(BasicBlock, self).__init__() self.conv1 = nn.Conv2d(inplanes, outplanes, kernel_size=3, stride=1, padding=1, bias=False) self.bn1 = nn.BatchNorm2d(outplanes) self.relu1 = nn.ReLU(inplace=True) self.conv2 = nn.Conv2d(outplanes, outplanes, kernel_size=3, stride=1, padding=1, bias=False) self.bn2 = nn.BatchNorm2d(outplanes) self.relu2 = nn.ReLU(inplace=True) def forward(self, x): residual = x out = self.conv1(x) out = self.bn1(out) out = self.relu1(out) out = self.conv2(out) out = self.bn2(out) out += residual out = self.relu2(out) return out class DenseBlock(nn.Module): def __init__(self, inplanes, outplanes, num_layers): super(DenseBlock, self).__init__() self.blocks = nn.ModuleList([BasicBlock(inplanes + i * outplanes, outplanes) for i in range(num_layers)]) def forward(self, x): features = [x] for block in self.blocks: y = block(torch.cat(features,dim=1)) features.append(y) return torch.cat(features,dim=1) class TransitionToFeatureMap(nn.Sequential): def __init__(self, inplanes, outplanes): super(TransitionToFeatureMap, self).__init__( nn.Conv2d(inplanes, outplanes, kernel_size=1), nn.BatchNorm2d(outplanes), nn.AvgPool2d(kernel_size=2, stride=2)) class DenseNet(nn.Module): def __init__(self, num_classes, growth_rate, layers_num): super(DenseNet, self).__init__() self.growth_rate = growth_rate self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = nn.BatchNorm2d(64) self.relu1 = nn.ReLU(inplace=True) self.layer1 = nn.Sequential( nn.MaxPool2d(kernel_size=3, stride=2, padding=1), DenseBlock(64, growth_rate, layers_num[0])) self.inplanes = 64 + growth_rate * layers_num[0] self.layer2 = nn.Sequential( TransitionToFeatureMap(self.inplanes, 128), DenseBlock(128, growth_rate, layers_num[1])) self.inplanes += growth_rate * layers_num[1] self.layer3 = nn.Sequential( TransitionToFeatureMap(self.inplanes, 256), DenseBlock(256, growth_rate, layers_num[2])) self.inplanes += growth_rate * layers_num[2] self.layer4 = nn.Sequential( TransitionToFeatureMap(self.inplanes, 512), DenseBlock(512, growth_rate, layers_num[3])) self.inplanes += growth_rate * layers_num[3] self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) self.fc = nn.Linear(self.inplanes, num_classes) def forward(self, x): x = self.conv1(x) x = self.bn1(x) x = self.relu1(x) x = self.layer1(x) x = self.layer2(x) x = self.layer3(x) x = self.layer4(x) x = self.avgpool(x) x = x.view(x.size(0), -1) x = self.fc(x) x = torch.sigmoid(x) return x def DenseNet121(num_classes): return DenseNet(num_classes=num_classes, growth_rate=32, layers_num=[6,12,24,16]) 复制代码 训练代码train.py： import torch import torch.nn as nn from torch.utils.data import DataLoader from torchvision.datasets import ImageFolder from torchvision import transforms from model import ResNet18 import matplotlib.pyplot as plt # 随机种子 torch.manual_seed(0) # 设置参数和数据路径 lr = 0.0001 num_epochs = 20 batch_size = 8 data_path = '/home/a504/mjw/Code/data_set/plantvillage_demo1' def main(): # 数据处理 transform_train = transforms.Compose([transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ToTensor()]) train_dataset = ImageFolder(root=data_path + '/train/', transform=transform_train) train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True) transform_val = transforms.Compose([transforms.Resize(256), transforms.CenterCrop(224), transforms.ToTensor()]) val_dataset = ImageFolder(root=data_path + '/val/', transform=transform_val) val_loader = DataLoader(dataset=val_dataset, batch_size=batch_size, shuffle=False) # 初始化模型 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = ResNet18(num_classes=len(train_dataset.classes)).to(device) # define loss function and optimizer criterion = nn.BCELoss() optimizer = torch.optim.Adam(model.parameters(), lr=lr) # 训练模型 train_losses = [] val_losses = [] for epoch in range(num_epochs): # 训练 train_loss = 0.0 model.train() for images, labels in train_loader: images, labels = images.to(device), labels.to(device) labels = nn.functional.one_hot(labels, num_classes=len(train_dataset.classes)).float() optimizer.zero_grad() # forward pass outputs = model(images) loss = criterion(outputs, labels) # backward pass and optimize loss.backward() optimizer.step() train_loss += loss.item() * images.size(0) train_loss = train_loss / len(train_loader.dataset) train_losses.append(train_loss) # validation val_loss = 0.0 model.eval() with torch.no_grad(): for images, labels in val_loader: images, labels = images.to(device), labels.to(device) labels = nn.functional.one_hot(labels, num_classes=len(val_dataset.classes)).float() outputs = model(images) loss = criterion(outputs, labels) val_loss += loss.item() * images.size(0) val_loss = val_loss / len(val_loader.dataset) val_losses.append(val_loss) print('Epoch [{}/{}], Train Loss: {:.4f}, Val Loss: {:.4f}'. format(epoch + 1, num_epochs, train_loss, val_loss)) # 保存训练数据 torch.save(model.state_dict(), 'resnet18_multi_label_classification.pth') # visualize the training process plt.plot(range(num_epochs), train_losses, '-b', label='train') plt.plot(range(num_epochs), val_losses, '-r', label='validation') plt.legend(loc='lower right') plt.xlabel('epoch') plt.ylabel('loss') plt.show() if __name__ == '__main__': main() 复制代码 预测代码predict.py： import torch import cv2 import numpy as np from model import ResNet18 import matplotlib.pyplot as plt # 加载模型 num_classes = 4 model = ResNet18(num_classes) model.load_state_dict(torch.load('vgg16_multi_label_classification.pth')) model.eval() # 加载并预处理图像 image_path = 'OIP-C.jpeg' image = cv2.imread(image_path) image = cv2.resize(image, (224, 224)) image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) image_normalized = (image / 255.0 - 0.5) / 0.5 input_tensor = torch.from_numpy(image_normalized.transpose(2, 0, 1)).float().unsqueeze(0) # 预测和可视化预测结果 with torch.no_grad(): output = model(input_tensor).squeeze().numpy() class_names = ['Apple___Apple_scab', 'Apple___Black_rot', 'Apple___Cedar_apple_rust', 'Apple___healthy'] # acquire top2 and probabilities top_indices = output.argsort()[-2:][::-1] top_probabilities = output[top_indices] top_class_names = [class_names[i] for i in top_indices] # 在图像上标记预测结果及概率 fig, ax = plt.subplots() ax.imshow(image) for idx, (class_name, prob) in enumerate(zip(top_class_names, top_probabilities)): plt.text(5, 15 + 20 * idx, f'{class_names[idx]}: {prob:.2f}', fontsize=12, color='red') plt.show() 复制代码 测试代码evaluate.py： import torch import torch.nn as nn from torch.utils.data import DataLoader from torchvision.datasets import ImageFolder from torchvision import transforms from tqdm import tqdm from model import ResNet18 # 常量和路径 num_classes = 4 model_path = './vgg16_multi_label_classification.pth' test_path = '/home/a504/mjw/Code/data_set/plantvillage_demo1/val' # 数据 transform_test = transforms.Compose([transforms.Resize(256), transforms.CenterCrop(224), transforms.ToTensor()]) test_dataset = ImageFolder(test_path, transform=transform_test) test_loader = DataLoader(test_dataset, batch_size=1, shuffle=False) # 模型 model = ResNet18(num_classes) model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu'))) model.eval() # define loss function criterion = nn.BCELoss() # 处理模型 hamming_loss = [] accuracy = [] precision = [] recall = [] f_beta = [] with torch.no_grad(): for idx, (images, labels) in tqdm(enumerate(test_loader), total=len(test_loader)): outputs = model(images) predicted = (outputs > 0.5).float() # threshold = 0.5 hamming_loss.append((predicted != labels.float()).sum().item() / (num_classes * len(labels))) tp = ((predicted == 1) & (labels.float() == 1)).sum().item() fp = ((predicted == 1) & (labels.float() == 0)).sum().item() tn = ((predicted == 0) & (labels.float() == 0)).sum().item() fn = ((predicted == 0) & (labels.float() == 1)).sum().item() accuracy.append((tp + tn) / (num_classes * len(labels))) precision.append(tp / (tp + fp + 1e-7)) recall.append(tp / (tp + fn + 1e-7)) f_beta.append(((1 + 0.5 ** 2) * precision[-1] * recall[-1]) / ((0.5 ** 2) * precision[-1] + recall[-1] + 1e-7)) print("Hamming Loss: {:.4f}".format(sum(hamming_loss) / len(hamming_loss))) print("Accuracy: {:.4f}".format(sum(accuracy) / len(accuracy))) print("Precision: {:.4f}".format(sum(precision) / len(precision))) print("Recall: {:.4f}".format(sum(recall) / len(recall))) print("F-beta Score: {:.4f}".format(sum(f_beta) / len(f_beta))) 复制代码
我来回答
( 粤ICP备18085999号-1 | 粤公网安备 44051102000585号)
狗仔卡
发表于 2023-4-23 16:40:51
置顶卡
千斤顶
显身卡
楼主