Fix tf.extract_image_patches documentation.

Fixes tensorflow#5770

PiperOrigin-RevId: 160696796

tensorflow/core/ops/array_ops.cc

@@ -4179,15 +4179,17 @@ Extract `patches` from `images` and put them in the "depth" output dimension.
 images: 4-D Tensor with shape `[batch, in_rows, in_cols, depth]`.
 patches: 4-D Tensor with shape `[batch, out_rows, out_cols, ksize_rows *
  ksize_cols * depth]` containing image patches with size
- `ksize_rows x ksize_cols x depth` vectorized in the "depth" dimension.
+ `ksize_rows x ksize_cols x depth` vectorized in the "depth" dimension. Note
+ `out_rows` and `out_cols` are the dimensions of the output patches.
 ksizes: The size of the sliding window for each dimension of `images`.
 strides: 1-D of length 4. How far the centers of two consecutive patches are in
  the images. Must be: `[1, stride_rows, stride_cols, 1]`.
 rates: 1-D of length 4. Must be: `[1, rate_rows, rate_cols, 1]`. This is the
  input stride, specifying how far two consecutive patch samples are in the
  input. Equivalent to extracting patches with
  `patch_sizes_eff = patch_sizes + (patch_sizes - 1) * (rates - 1)`, followed by
- subsampling them spatially by a factor of `rates`.
+ subsampling them spatially by a factor of `rates`. This is equivalent to
+ `rate` in dilated (a.k.a. Atrous) convolutions.
 padding: The type of padding algorithm to use.
 
 We specify the size-related attributes as: