diff --git a/models.py b/models.py
index 2d88c47d..d36640a0 100755
--- a/models.py
+++ b/models.py
@@ -33,7 +33,7 @@ def create_modules(module_defs):
             if bn:
                 modules.add_module('batch_norm_%d' % i, nn.BatchNorm2d(filters))
             if module_def['activation'] == 'leaky':
-                modules.add_module('leaky_%d' % i, nn.LeakyReLU(0.1))
+                modules.add_module('leaky_%d' % i, nn.LeakyReLU(0.1, inplace=True))
 
         elif module_def['type'] == 'maxpool':
             kernel_size = int(module_def['size'])
diff --git a/train.py b/train.py
index c00ad68c..720e0b1e 100644
--- a/train.py
+++ b/train.py
@@ -49,7 +49,6 @@ def train(
     start_epoch = 0
     best_loss = float('inf')
     nf = int(model.module_defs[model.yolo_layers[0] - 1]['filters'])  # yolo layer size (i.e. 255)
-
     if resume:  # Load previously saved model
         if transfer:  # Transfer learning
             chkpt = torch.load(weights + 'yolov3.pt', map_location=device)
@@ -74,7 +73,7 @@ def train(
         else:
             cutoff = load_darknet_weights(model, weights + 'darknet53.conv.74')
 
-    # Set scheduler (reduce lr at epochs 218, 245, i.e. batches 400k, 450k)
+    # Scheduler (reduce lr at epochs 218, 245, i.e. batches 400k, 450k)
     scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=[218, 245], gamma=0.1,
                                                      last_epoch=start_epoch - 1)
 
diff --git a/utils/utils.py b/utils/utils.py
index fa24b07f..bfdddeef 100755
--- a/utils/utils.py
+++ b/utils/utils.py
@@ -326,7 +326,6 @@ def build_targets(model, targets):
     return txy, twh, tcls, indices
 
 
-# @profile
 def non_max_suppression(prediction, conf_thres=0.5, nms_thres=0.5):
     """
     Removes detections with lower object confidence score than 'conf_thres'
@@ -383,6 +382,11 @@ def non_max_suppression(prediction, conf_thres=0.5, nms_thres=0.5):
             dc = pred[pred[:, -1] == c]  # select class c
             dc = dc[:min(len(dc), 100)]  # limit to first 100 boxes: https://github.com/ultralytics/yolov3/issues/117
 
+            # No NMS required if only 1 prediction
+            if len(dc) == 1:
+                det_max.append(dc)
+                continue
+
             # Non-maximum suppression
             if nms_style == 'OR':  # default
                 # METHOD1
@@ -410,6 +414,9 @@ def non_max_suppression(prediction, conf_thres=0.5, nms_thres=0.5):
 
             elif nms_style == 'MERGE':  # weighted mixture box
                 while len(dc):
+                    if len(dc) == 1:
+                        det_max.append(dc)
+                        break
                     i = bbox_iou(dc[0], dc) > nms_thres  # iou with other boxes
                     weights = dc[i, 4:5]
                     dc[0, :4] = (weights * dc[i, :4]).sum(0) / weights.sum()