张量流中补丁的点积

Question

我有两个大小相同的方阵和一个方块的尺寸。我想计算每对补丁之间的点积。本质上我想实现以下操作：

def patch_dot(A, B, patch_dim):
    res_dim = A.shape[0] - patch_dim + 1
    res = np.zeros([res_dim, res_dim, res_dim, res_dim])
    for i in xrange(res_dim):
        for j in xrange(res_dim):
            for k in xrange(res_dim):
                for l in xrange(res_dim):
                    res[i, j, k, l] = (A[i:i + patch_dim, j:j + patch_dim] *
                                       B[k:k + patch_dim, l:l + patch_dim]).sum()

    return res

显然这是一个非常低效的实现。 Tensorflow 的 tf.nn.conv2d 似乎是一个自然的解决方案，因为我本质上是在做一个卷积，但是我的过滤器矩阵不是固定的。在 Tensorflow 中是否有自然的解决方案，或者我应该开始考虑实现我自己的 tf-op？

Answer 1

执行此操作的自然方法是首先使用 tf.extract_image_patches, then to apply the tf.nn.conv2D function on A and each B sub-patch using tf.map_fn.

提取矩阵 B 的重叠图像块

注意使用前tf.extract_image_patches and tf.nn.conv2D you need to reshape your matrices as 4D tensors of shape [1, width, height, 1] using tf.reshape.

此外，在使用之前 tf.map_fn, you would also need to use the tf.transpose op so that the B sub-patches are indexed by the first dimension of the tensor you use as the elems argument of tf.map_fn。

张量流中补丁的点积

Dot product of patches in tensorflow

python

machine-learning

linear-algebra

computer-vision

tensorflow