Minor: Simple Documentation Fixes.

official/vision/beta/projects/yolo/README.md

@@ -17,9 +17,9 @@ repository.
 
 ## Description
 
-YOLO v1 the original implementation was released in 2015 providing a 
-groundbreakingalgorithm that would quickly process images and locate objects in 
-a single pass through the detector. The original implementation used a
+YOLO v1 the original implementation was released in 2015 providing a
+ground breaking algorithm that would quickly process images and locate objects
+in a single pass through the detector. The original implementation used a
 backbone derived from state of the art object classifiers of the time, like
 [GoogLeNet](https://arxiv.org/abs/1409.4842) and
 [VGG](https://arxiv.org/abs/1409.1556). More attention was given to the novel
@@ -32,14 +32,14 @@ update and develop this model.
 
 YOLO v3 and v4 serve as the most up to date and capable versions of the YOLO
 network group. This model uses a custom backbone called Darknet53 that uses
-knowledge gained from the ResNet paper to improve its predictions. The new 
-backbone also allows for objects to be detected at multiple scales. As for the 
-new detection head, the model now predicts the bounding boxes using a set of 
-anchor box priors (Anchor Boxes) as suggestions. Multiscale predictions in 
-combination with Anchor boxes allow for the network to make up to 1000 object 
-predictions on a single image. Finally, the new loss function forces the network 
+knowledge gained from the ResNet paper to improve its predictions. The new
+backbone also allows for objects to be detected at multiple scales. As for the
+new detection head, the model now predicts the bounding boxes using a set of
+anchor box priors (Anchor Boxes) as suggestions. Multiscale predictions in
+combination with Anchor boxes allow for the network to make up to 1000 object
+predictions on a single image. Finally, the new loss function forces the network
 to make better predictions by using Intersection Over Union (IOU) to inform the
-model's confidence rather than relying on the mean squared error for the entire 
+model's confidence rather than relying on the mean squared error for the entire
 output.
 
 
@@ -80,5 +80,5 @@ connected to a new, more powerful backbone if a person chose to.
 [![Python 3.8](https://img.shields.io/badge/Python-3.8-3776AB)](https://www.python.org/downloads/release/python-380/)
 
 
-DISCLAIMER: this YOLO implementation is still under development. No support 
+DISCLAIMER: this YOLO implementation is still under development. No support
 will be provided during the development phase.

official/vision/beta/projects/yolo/ops/nms_ops.py

@@ -8,13 +8,13 @@ class TiledNMS():
   IOU_TYPES = {'diou': 0, 'giou': 1, 'ciou': 2, 'iou': 3}
 
   def __init__(self, iou_type='diou', beta=0.6):
-    '''Initialization for all non max suppression operations mainly used to
+    """Initialization for all non max suppression operations mainly used to
     select hyperparameters for the iou type and scaling.
 
     Args:
       iou_type: `str` for the version of IOU to use {diou, giou, ciou, iou}.
       beta: `float` for the amount to scale regularization on distance iou.
-    '''
+    """
     self._iou_type = TiledNMS.IOU_TYPES[iou_type]
     self._beta = beta
 
@@ -326,8 +326,10 @@ def sorted_non_max_suppression_padded(scores, boxes, max_output_size,
 
 
 def sort_drop(objectness, box, classificationsi, k):
-  """This function sorts and drops boxes such that there are only k boxes
-  sorted by number the objectness or confidence
+  """This function sorts and then drops boxes.
+
+  Boxes are sorted and dropped such that there are only k boxes sorted by the
+  objectness or confidence.
 
   Args:
     objectness: a `Tensor` of shape [batch size, N] that needs to be
@@ -447,7 +449,7 @@ def nms(boxes,
   boxes, classes, confidence = segment_nms(boxes, classes, confidence,
                                            prenms_top_k, nms_thresh)
 
-  # sort the classes of the unspressed boxes
+  # sort the classes of the unsuppressed boxes
   class_confidence, class_ind = tf.math.top_k(
       classes, k=tf.shape(classes)[-1], sorted=True)