请写一个利用CWRU数据做s变换时频图数据集输入resnet18网络进行迁移学习的t-sne代码

以下是一个利用CWRU数据做s变换时频图数据集输入resnet18网络进行迁移学习的t-sne代码，供您参考：

import numpy as np
import matplotlib.pyplot as plt
from sklearn.manifold import TSNE
from sklearn.preprocessing import normalize
import torch
import torch.nn as nn
import torchvision.models as models
from torchvision import transforms, datasets

# Load CWRU dataset
data_transform = transforms.Compose([
    transforms.Resize(224),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.5], std=[0.5])
])

train_dataset = datasets.ImageFolder(
    root='./cwru_spectrogram/train',
    transform=data_transform
)

train_loader = torch.utils.data.DataLoader(
    train_dataset, batch_size=64, shuffle=False
)

# Load pretrained ResNet18 model
pretrained_model = models.resnet18(pretrained=True)
pretrained_model.fc = nn.Linear(512, 10)

# Create new ResNet18 model with pretrained weights
model = models.resnet18(pretrained=False)
model.fc = nn.Linear(512, 10)
model.load_state_dict(pretrained_model.state_dict())

# Freeze all layers except the last fully connected layer
for param in model.parameters():
    param.requires_grad = False

for param in model.fc.parameters():
    param.requires_grad = True

# Train the model
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.fc.parameters(), lr=0.001)

num_epochs = 10
for epoch in range(num_epochs):
    running_loss = 0.0
    for i, (inputs, labels) in enumerate(train_loader):
        inputs = inputs.to(device)
        labels = labels.to(device)

        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, labels)

        loss.backward()
        optimizer.step()

        running_loss += loss.item()

    print('Epoch [{}/{}], Loss: {:.4f}'
          .format(epoch+1, num_epochs, running_loss))

# Get feature vectors from ResNet18
feature_vectors = []
for inputs, labels in train_loader:
    inputs = inputs.to(device)
    feature_vector = model(inputs).detach().cpu().numpy()
    feature_vectors.append(feature_vector)

feature_vectors = np.vstack(feature_vectors)

# Normalize feature vectors
feature_vectors = normalize(feature_vectors, norm='l2')

# Perform t-SNE
tsne = TSNE(n_components=2, perplexity=30, learning_rate=200)
tsne_results = tsne.fit_transform(feature_vectors)

# Plot t-SNE results
plt.scatter(tsne_results[:, 0], tsne_results[:, 1], c=train_dataset.targets)
plt.show()

请注意，这只是一个示例代码，需要您根据您的实际数据和需求进行修改和调整。同时，由于迁移学习的训练过程比较耗时，建议在GPU上运行代码以获得更好的性能。