Question

我加载了形状为（10000，28，28，1）的MNIST（测试）数据集（表示10000张图像（灰度28x28图像））。我想在每个图像上应用运动模糊内核，并获得同样形状的输出（10000、28、28、1）。我尝试使用def，vectorize，但无法按预期工作。

它在python 3.6上运行

x_test.shape
--> (numpy.ndarray) (10000, 28, 28, 1)


def blurize(x):
    # kernel
    k = np.array([[0,0,0,0,0,0,0.0013],
    [0,0,0,0.0086,0.0574,0.1061,0.1165],
    [0,0.0450,0.0938,0.1426,0.0938,0.0450,0],
    [0.1165,0.1061,0.0574,0.0086,0,0,0],
    [0.0013,0,0,0,0,0,0]])
    return (ndimage.convolve(x.reshape(28,28), k, mode='constant', cval=0.0))

blurred = blurize(x_test)
plt.imshow(blurred[1], interpolation='none', cmap='gray')
plt.show()

结果：

ValueError: cannot reshape array of size 7840000 into shape (28,28)

如果我尝试过 blurred = blurize(x_test[1]).有效，但仅适用于第二张图像。由于我不想通过x_test [i]遍历整个数组并将帧再次合并为预期的输出数组（10000，28，28，1）。谢谢。

Answer 1

您可以squeeze输入数组，广播内核，然后调整输出形状以匹配初始尺寸：

ndimage.convolve(x.squeeze(), k[None, ...], mode='constant', cval=0.0)[..., None]

将函数应用于4d数组的每个维度，并在python中返回4d数组

1 个答案: