[TOPI] Fixed nms max_output_size loop (apache#4541)

One of the loops in hybrid_nms used for
performing the max_output_size reordering
was incorrectly designated as parallel
resulting in incorrect behaviour. This patch
changes that loop to a serial loop.

Change-Id: I97184f5887f5f028d8ab339fa2808eb7630a4017

Author: mbaret

topi/python/topi/vision/nms.py

@@ -278,7 +278,7 @@ def hybrid_nms(data, sorted_index, valid_count,
         # Only return max_output_size valid boxes
         num_valid_boxes = 0
         if max_output_size > 0:
-            for j in parallel(valid_count[i]):
+            for j in range(valid_count[i]):
                 if output[i, j, 0] >= zero:
                     if num_valid_boxes == max_output_size:
                         for k in range(box_data_length):