Reuse de_parallel() rather than is_parallel() (#6354)

utils/torch_utils.py

@@ -295,7 +295,7 @@ class ModelEMA:
 
     def __init__(self, model, decay=0.9999, updates=0):
         # Create EMA
-        self.ema = deepcopy(model.module if is_parallel(model) else model).eval()  # FP32 EMA
+        self.ema = deepcopy(de_parallel(model)).eval()  # FP32 EMA
         # if next(model.parameters()).device.type != 'cpu':
         #     self.ema.half()  # FP16 EMA
         self.updates = updates  # number of EMA updates
@@ -309,7 +309,7 @@ class ModelEMA:
             self.updates += 1
             d = self.decay(self.updates)
 
-            msd = model.module.state_dict() if is_parallel(model) else model.state_dict()  # model state_dict
+            msd = de_parallel(model).state_dict()  # model state_dict
             for k, v in self.ema.state_dict().items():
                 if v.dtype.is_floating_point:
                     v *= d