Fixed typos in non_max_suppression_padded
diff --git a/tensorflow/python/ops/image_ops_impl.py b/tensorflow/python/ops/image_ops_impl.py
index bbce257..ab57ce9 100644
--- a/tensorflow/python/ops/image_ops_impl.py
+++ b/tensorflow/python/ops/image_ops_impl.py
@@ -4578,7 +4578,7 @@
sorted_input: a boolean indicating whether the input boxes and scores
are sorted in descending order by the score.
canonicalized_coordinates: if box coordinates are given as
- `[y_min, x_min, y_max, x_max]`, settign to True eliminate redundant
+ `[y_min, x_min, y_max, x_max]`, setting to True eliminate redundant
computation to canonicalize box coordinates.
tile_size: an integer representing the number of boxes in a tile, i.e.,
the maximum number of boxes per image that can be used to suppress other
@@ -4586,8 +4586,8 @@
potentially more redundant work.
Returns:
idx: a tensor with a shape of [..., num_boxes] representing the
- indices selected by non-max suppression. The leadign dimensions
- are the batch dimensions of the input boxes. All numbers are are within
+ indices selected by non-max suppression. The leading dimensions
+ are the batch dimensions of the input boxes. All numbers are within
[0, num_boxes). For each image (i.e., idx[i]), only the first num_valid[i]
indices (i.e., idx[i][:num_valid[i]]) are valid.
num_valid: a tensor of rank 0 or higher with a shape of [...]
@@ -4703,7 +4703,7 @@
sorted_input: a boolean indicating whether the input boxes and scores
are sorted in descending order by the score.
canonicalized_coordinates: if box coordinates are given as
- `[y_min, x_min, y_max, x_max]`, settign to True eliminate redundant
+ `[y_min, x_min, y_max, x_max]`, setting to True eliminate redundant
computation to canonicalize box coordinates.
tile_size: an integer representing the number of boxes in a tile, i.e.,
the maximum number of boxes per image that can be used to suppress other
@@ -4711,8 +4711,8 @@
potentially more redundant work.
Returns:
idx: a tensor with a shape of [..., num_boxes] representing the
- indices selected by non-max suppression. The leadign dimensions
- are the batch dimensions of the input boxes. All numbers are are within
+ indices selected by non-max suppression. The leading dimensions
+ are the batch dimensions of the input boxes. All numbers are within
[0, num_boxes). For each image (i.e., idx[i]), only the first num_valid[i]
indices (i.e., idx[i][:num_valid[i]]) are valid.
num_valid: a tensor of rank 0 or higher with a shape of [...]