Update base_backbone.py

Solve the problem：
RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicate
s that your module has parameters that were not used in producing loss. You can enable unused parameter detection by passing the keyword argument `find_unused_parameters=True` to `torch.nn.parallel.DistributedDataParallel`, and by
making sure all `forward` function outputs participate in calculating loss.

reference:
open-mmlab/mmdetection#8208 (comment)

mmyolo/models/backbones/base_backbone.py

@@ -118,6 +118,8 @@ def __init__(self,
                 stage += self.make_stage_plugins(plugins, idx, setting)
             self.add_module(f'stage{idx + 1}', nn.Sequential(*stage))
             self.layers.append(f'stage{idx + 1}')
+
+        self._freeze_stages()
 
     @abstractmethod
     def build_stem_layer(self):