忽略填充参数和尾随窗口，这些窗口的长度不足以针对第二个数组进行卷积，这是一种方法
np.lib.stride_tricks.as_strided-
def strided4D(arr,arr2,s): strided = np.lib.stride_tricks.as_strided s0,s1 = arr.strides m1,n1 = arr.shape m2,n2 = arr2.shape out_shp = (1+(m1-m2)//s, m2, 1+(n1-n2)//s, n2) return strided(arr, shape=out_shp, strides=(s*s0,s*s1,s0,s1))def stride_conv_strided(arr,arr2,s): arr4D = strided4D(arr,arr2,s=s) return np.tensordot(arr4D, arr2, axes=((2,3),(0,1)))
另外，我们可以使用内置的scikit-image
view_as_windows来 优雅
地获取那些窗口，就像这样-
from skimage.util.shape import view_as_windowsdef strided4D_v2(arr,arr2,s): return view_as_windows(arr, arr2.shape, step=s)
