我正在使用 K 均值聚類算法執(zhí)行圖像壓縮。壓縮后得到的圖像是灰度圖像，如何獲得與原始圖像質(zhì)量相近的彩色圖像？import osfrom skimage import iofrom sklearn.cluster import  MiniBatchKMeansimport numpy as npalgorithm = "full"for f in os.listdir('.'):    if f.endswith('.png'):        image = io.imread(f)        rows = image.shape[0]        cols = image.shape[1]        image = image.reshape(image.shape[0] * image.shape[1], image.shape[2])        kmeans = MiniBatchKMeans(n_clusters=128, n_init=10, max_iter=200)        kmeans.fit(image)        clusters = np.asarray(kmeans.cluster_centers_, dtype=np.uint8)        labels = np.asarray(kmeans.labels_, dtype=np.uint8)        labels = labels.reshape(rows, cols);        #  np.save('codebook'+f+'.npy', clusters)        io.imsave('compressed_' + f , labels);