基于pytorch的图像分割脚本（python示例）

代码

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision.datasets import ImageFolder
from tqdm import tqdm

# 定义数据预处理
transform = transforms.Compose([
    transforms.Resize((256, 256)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[.485, .456, .406], std=[.229, .224, .225])
])

# 加载数据集
dataset = ImageFolder('path/to/dataset', transform=transform)
dataloader = DataLoader(dataset, batch_size=4, shuffle=True)

# 定义模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, padding=1)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu1 = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(64, 64, kernel_size=3, padding=1)
        self.bn2 = nn.BatchNorm2d(64)
        self.relu2 = nn.ReLU(inplace=True)
        self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv3 = nn.Conv2d(64, 128, kernel_size=3, padding=1)
        self.bn3 = nn.BatchNorm2d(128)
        self.relu3 = nn.ReLU(inplace=True)
        self.conv4 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
        self.bn4 = nn.BatchNorm2d(128)
        self.relu4 = nn.ReLU(inplace=True)
        self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv5 = nn.Conv2d(128, 256, kernel_size=3, padding=1)
        self.bn5 = nn.BatchNorm2d(256)
        self.relu5 = nn.ReLU(inplace=True)
        self.conv6 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
        self.bn6 = nn.BatchNorm2d(256)
        self.relu6 = nn.ReLU(inplace=True)
        self.conv7 = nn.Conv2d(256, 256, kernel_size=3, padding=1)
        self.bn7 = nn.BatchNorm2d(256)
        self.relu7 = nn.ReLU(inplace=True)
        self.pool3 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv8 = nn.Conv2d(256, 512, kernel_size=3, padding=1)
        self.bn8 = nn.BatchNorm2d(512)
        self.relu8 = nn.ReLU(inplace=True)
        self.conv9 = nn.Conv2d(512, 512, kernel_size=3, padding=1)
        self.bn9 = nn.BatchNorm2d(512)
        self.relu9 = nn.ReLU(inplace=True)
        self.conv10 = nn.Conv2d(512, 512, kernel_size=3, padding=1)
        self.bn10 = nn.BatchNorm2d(512)
        self.relu10 = nn.ReLU(inplace=True)
        self.pool4 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv11 = nn.Conv2d(512, 512, kernel_size=3, padding=1)
        self.bn11 = nn.BatchNorm2d(512)
        self.relu11 = nn.ReLU(inplace=True)
        self.conv12 = nn.Conv2d(512, 512, kernel_size=3, padding=1)
        self.bn12 = nn.BatchNorm2d(512)
        self.relu12 = nn.ReLU(inplace=True)
        self.conv13 = nn.Conv2d(512, 512, kernel_size=3, padding=1)
        self.bn13 = nn.BatchNorm2d(512)
        self.relu13 = nn.ReLU(inplace=True)
        self.pool5 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.fc1 = nn.Linear(512 * 8 * 8, 4096)
        self.relu14 = nn.ReLU(inplace=True)
        self.dropout1 = nn.Dropout()
        self.fc2 = nn.Linear(4096, 4096)
        self.relu15 = nn.ReLU(inplace=True)
        self.dropout2 = nn.Dropout()
        self.fc3 = nn.Linear(4096, 2)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu1(x)
        x = self.conv2(x)
        x = self.bn2(x)
        x = self.relu2(x)
        x = self.pool1(x)
        x = self.conv3(x)
        x = self.bn3(x)
        x = self.relu3(x)
        x = self.conv4(x)
        x = self.bn4(x)
        x = self.relu4(x)
        x = self.pool2(x)
        x = self.conv5(x)
        x = self.bn5(x)
        x = self.relu5(x)
        x = self.conv6(x)
        x = self.bn6(x)
        x = self.relu6(x)
        x = self.conv7(x)
        x = self.bn7(x)
        x = self.relu7(x)
        x = self.pool3(x)
        x = self.conv8(x)
        x = self.bn8(x)
        x = self.relu8(x)
        x = self.conv9(x)
        x = self.bn9(x)
        x = self.relu9(x)
        x = self.conv10(x)
        x = self.bn10(x)
        x = self.relu10(x)
        x = self.pool4(x)
        x = self.conv11(x)
        x = self.bn11(x)
        x = self.relu11(x)
        x = self.conv12(x)
        x = self.bn12(x)
        x = self.relu12(x)
        x = self.conv13(x)
        x = self.bn13(x)
        x = self.relu13(x)
        x = self.pool5(x)
        x = x.view(-1, 512 * 8 * 8)
        x = self.fc1(x)
        x = self.relu14(x)
        x = self.dropout1(x)
        x = self.fc2(x)
        x = self.relu15(x)
        x = self.dropout2(x)
        x = self.fc3(x)
        return x

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=.001)

# 训练模型
net = Net()
net.train()
for epoch in range(10):
    running_loss = .
    for inputs, labels in tqdm(dataloader):
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item() * inputs.size()
    epoch_loss = running_loss / len(dataset)
    print('Epoch {} loss: {:.4f}'.format(epoch+1, epoch_loss))

Statement

本代码未经系统测试及专业测评