我想为MNIST DIGITS数据集中的图像创建一个k -nearest邻居图,并带有用户定义的距离度量 - 为简单起见,为简单起见,frobenius a -b norm a -b norm。
sklearn.neighbors.kneighbors_graph提供了一个不错的接口,但不允许矩阵值数据 - 例如。当我尝试按下图表时:
from torchvision.datasets import MNIST
import sklearn
# Define distance metric for matrices
metric_func = lambda X, Y: norm(X - Y, ord='fro')
data = MNIST('sample_data', train=True, transform=None, target_transform=None, download=True)
adj_matrix = sklearn.neighbors.kneighbors_graph(
data.data,
n_neighbors=5,
mode='connectivity',
metric=metric_func,
p=2,
metric_params=None,
include_self=False,
n_jobs=None
)
我得到错误:
ValueError: Found array with dim 3. Estimator expected <= 2.
我可以写自己的'kneighbors_graph((`方法,但它可能涉及循环和大量效率的双倍。是否有一种有效的方法可以在Python中创建此图?
弄平图像
from sklearn import datasets
from sklearn.neighbors import kneighbors_graph
digits = datasets.load_digits()
images = digits.data.reshape(-1, 8, 8)
distances = kneighbors_graph(images.reshape(-1, 64), 5, mode='distance', include_self=True, metric='euclidean')
distances = distances.todense()
# Test
i = 11
print ("Actual Image: {0}, Nearest 5 Images: {1}".format(
digits.target[i], digits.target[distances[i].nonzero()[1]]))
输出: Actual Image: 1, Nearest 5 Images: [1 1 1 1]
这很简单,它期望有2D(2维(数组作为x:
的输入https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.kneighbors_graph.html
您提供了一个吗?检查,data.data.shape
返回什么?