bug fix for torch.max operation

RuntimeError: Expected object of scalar type Byte but got scalar type Bool for argument sgrvinod#2 'other' in call to _th_max

Author: dodiku

model.py

@@ -491,7 +491,8 @@ def detect_objects(self, predicted_locs, predicted_scores, min_score, max_overla
 
                     # Suppress boxes whose overlaps (with this box) are greater than maximum overlap
                     # Find such boxes and update suppress indices
-                    suppress = torch.max(suppress, overlap[box] > max_overlap)
+                    overlap_above_max = (overlap[box] > max_overlap).byte()
+                    suppress = torch.max(suppress, overlap_above_max)
                     # The max operation retains previously suppressed boxes, like an 'OR' operation
 
                     # Don't suppress this box, even though it has an overlap of 1 with itself