Refactor out-of-place `Detect()` for reduced ops (#7257)

models/yolo.py

                     y[..., 0:2] = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
                     y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
                 else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
-                    xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    xy = (y[..., 0:2] * 2 + (self.grid[i] - 0.5)) * self.stride[i]  # xy
                     wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
-                    y = torch.cat((xy, wh, y[..., 4:]), -1)
+                    y = torch.cat((xy, wh, y[..., 4:]), 4)
                 z.append(y.view(bs, -1, self.no))
 
         return x if self.training else (torch.cat(z, 1), x)