diff --git a/models/yolo.py b/models/yolo.py
index 9eddf4a08e49..0a27b24dede7 100644
--- a/models/yolo.py
+++ b/models/yolo.py
@@ -98,7 +98,6 @@ def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, i
         self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
         self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
         self.inplace = self.yaml.get('inplace', True)
-        # LOGGER.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
 
         # Build strides, anchors
         m = self.model[-1]  # Detect()
@@ -110,7 +109,6 @@ def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, i
             check_anchor_order(m)
             self.stride = m.stride
             self._initialize_biases()  # only run once
-            # LOGGER.info('Strides: %s' % m.stride.tolist())
 
         # Init weights, biases
         initialize_weights(self)
@@ -119,47 +117,33 @@ def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, i
 
     def forward(self, x, augment=False, profile=False, visualize=False):
         if augment:
-            return self.forward_augment(x)  # augmented inference, None
-        return self.forward_once(x, profile, visualize)  # single-scale inference, train
+            return self._forward_augment(x)  # augmented inference, None
+        return self._forward_once(x, profile, visualize)  # single-scale inference, train
 
-    def forward_augment(self, x):
+    def _forward_augment(self, x):
         img_size = x.shape[-2:]  # height, width
         s = [1, 0.83, 0.67]  # scales
         f = [None, 3, None]  # flips (2-ud, 3-lr)
         y = []  # outputs
         for si, fi in zip(s, f):
             xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
-            yi = self.forward_once(xi)[0]  # forward
+            yi = self._forward_once(xi)[0]  # forward
             # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
             yi = self._descale_pred(yi, fi, si, img_size)
             y.append(yi)
         return torch.cat(y, 1), None  # augmented inference, train
 
-    def forward_once(self, x, profile=False, visualize=False):
+    def _forward_once(self, x, profile=False, visualize=False):
         y, dt = [], []  # outputs
         for m in self.model:
             if m.f != -1:  # if not from previous layer
                 x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
-
             if profile:
-                c = isinstance(m, Detect)  # copy input as inplace fix
-                o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
-                t = time_sync()
-                for _ in range(10):
-                    m(x.copy() if c else x)
-                dt.append((time_sync() - t) * 100)
-                if m == self.model[0]:
-                    LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s}  {'module'}")
-                LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f}  {m.type}')
-
+                self._profile_one_layer(m, x, dt)
             x = m(x)  # run
             y.append(x if m.i in self.save else None)  # save output
-
             if visualize:
                 feature_visualization(x, m.type, m.i, save_dir=visualize)
-
-        if profile:
-            LOGGER.info('%.1fms total' % sum(dt))
         return x
 
     def _descale_pred(self, p, flips, scale, img_size):
@@ -179,6 +163,19 @@ def _descale_pred(self, p, flips, scale, img_size):
             p = torch.cat((x, y, wh, p[..., 4:]), -1)
         return p
 
+    def _profile_one_layer(self, m, x, dt):
+        c = isinstance(m, Detect)  # is final layer, copy input as inplace fix
+        o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
+        t = time_sync()
+        for _ in range(10):
+            m(x.copy() if c else x)
+        dt.append((time_sync() - t) * 100)
+        if m == self.model[0]:
+            LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s}  {'module'}")
+        LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f}  {m.type}')
+        if c:
+            LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s}  Total")
+
     def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
         # https://arxiv.org/abs/1708.02002 section 3.3
         # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.