Refactor Detect() anchors for ONNX <> OpenCV DNN compatibility (#4833)

* refactor anchors and anchor_grid in Detect Layer

* fix CI failures by adding compatibility

* fix tf failure

* fix different devices errors

* Cleanup

* fix anchors overwriting issue

* better refactoring

* Remove self.anchor_grid shape check (redundant with self.grid check)

Also PEP8 / 120 line width

* Convert _make_grid() from static to dynamic method

* Remove anchor_grid.to(device)

clone() should already clone to same device as self.anchors

* fix different devices error

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

models/common.py

@@ -295,6 +295,8 @@ class AutoShape(nn.Module):
         m = self.model.model[-1]  # Detect()
         m.stride = fn(m.stride)
         m.grid = list(map(fn, m.grid))
+        if isinstance(m.anchor_grid, list):
+            m.anchor_grid = list(map(fn, m.anchor_grid))
         return self
 
     @torch.no_grad()