torch.jit.trace() fix (#9363)

* Update common.py

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Update ci-testing.yml

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

models/common.py

@@ -600,6 +600,7 @@ class AutoShape(nn.Module):
         if self.pt:
             m = self.model.model.model[-1] if self.dmb else self.model.model[-1]  # Detect()
             m.inplace = False  # Detect.inplace=False for safe multithread inference
+            m.export = True  # do not output loss values
 
     def _apply(self, fn):
         # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers