可以给我一个完整的代码

当然可以，以下是完整的代码，包括读取PNG图像、ResNet50特征提取、KMeans聚类和层次聚类方法：

import os
import cv2
import numpy as np
import torch
import torchvision.models as models
from sklearn.cluster import KMeans
from scipy.cluster.hierarchy import linkage, fcluster
from scipy.spatial.distance import pdist

# 读取PNG图像并将其转换为NumPy数组
def read_png_image(file_path):
    image = cv2.imread(file_path)
    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    image = cv2.resize(image, (224, 224))
    image = np.array(image, dtype=np.float32) / 255.0
    return image

# 读取所有PNG图像
images = []
for filename in os.listdir('D:/wjd'):
    if filename.endswith('.png'):
        file_path = os.path.join('D:/wjd', filename)
        image = read_png_image(file_path)
        images.append(image)

# 加载预训练的ResNet50模型
model = models.resnet50(pretrained=True)
model = torch.nn.Sequential(*(list(model.children())[:-1]))
model.eval()

# 提取图像特征
features = []
for image in images:
    image = np.expand_dims(image, axis=0)
    image = torch.from_numpy(image).permute(0, 3, 1, 2)
    with torch.no_grad():
        feature = model(image).numpy().squeeze()
        features.append(feature)

# 使用KMeans算法对特征进行聚类
kmeans = KMeans(n_clusters=5)
clusters = kmeans.fit_predict(features)

# 使用层次聚类方法将图像分成更多类
distance_matrix = pdist(features, metric='euclidean')
linkage_matrix = linkage(distance_matrix, method='ward')
labels = fcluster(linkage_matrix, t=250, criterion='distance')

# 输出聚类结果
print('KMeans聚类结果：', clusters)
print('层次聚类结果：', labels)

注意，这里的代码仅作为示例，您可能需要根据您的具体需求进行调整。