CODEWITHSUNDEEP
pythonmachine-learningcomputer-visiontensorflowlinear-algebra
Karl
Karl

Reputation: 87

Dot product of patches in tensorflow

I have two square matrices of the same size and the dimensions of a square patch. I'd like to compute the dot product between every pair of patches. Essentially I would like to implement the following operation:

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

Obviously this would be an extremely inefficient implementation. Tensorflow's tf.nn.conv2d seems like a natural solution to this as I'm essentially doing a convolution, however my filter matrix isn't fixed. Is there a natural solution to this in Tensorflow, or should I start looking at implementing my own tf-op?

Upvotes: 1

Views: 457

Answers (1)

user2682877
user2682877

Reputation: 550

The natural way to do this is to first extract overlapping image patches of matrix B using tf.extract_image_patches, then to apply the tf.nn.conv2D function on A and each B sub-patch using tf.map_fn.

Note that prior to use 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.

Also, prior to use 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.

Upvotes: 1

Related Questions