Improved BGR2RGB speeds (#3880)

* Update BGR2RGB ops

* speed improvements

* cleanup

models/common.py

@@ -259,7 +259,7 @@ class AutoShape(nn.Module):
             files.append(Path(f).with_suffix('.jpg').name)
             if im.shape[0] < 5:  # image in CHW
                 im = im.transpose((1, 2, 0))  # reverse dataloader .transpose(2, 0, 1)
-            im = im[:, :, :3] if im.ndim == 3 else np.tile(im[:, :, None], 3)  # enforce 3ch input
+            im = im[..., :3] if im.ndim == 3 else np.tile(im[..., None], 3)  # enforce 3ch input
             s = im.shape[:2]  # HWC
             shape0.append(s)  # image shape
             g = (size / max(s))  # gain