[bugfix] EMAHook load state dict

[okotaku]

Motivation

When using yolox, it raised an error because of fixed num_classes in head.

  File "/opt/site-packages/mmdet/.mim/tools/train.py", line 120, in <module>
    main()
  File "/opt/site-packages/mmdet/.mim/tools/train.py", line 116, in main
    runner.train()
  File "/opt/conda/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1623, in train
    self.load_or_resume()
  File "/opt/conda/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1585, in load_or_resume
    self.load_checkpoint(self._load_from)
  File "/opt/conda/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1977, in load_checkpoint
    self.call_hook('after_load_checkpoint', checkpoint=checkpoint)
  File "/opt/conda/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1693, in call_hook
    getattr(hook, fn_name)(self, **kwargs)
  File "/opt/conda/lib/python3.8/site-packages/mmengine/hooks/ema_hook.py", line 187, in after_load_checkpoint
    self.ema_model.module.load_state_dict(
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1605, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for YOLOX:
        size mismatch for bbox_head.multi_level_conv_cls.0.weight: copying a param with shape torch.Size([80, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 128, 1, 1]).
        size mismatch for bbox_head.multi_level_conv_cls.0.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([3]).
        size mismatch for bbox_head.multi_level_conv_cls.1.weight: copying a param with shape torch.Size([80, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 128, 1, 1]).
        size mismatch for bbox_head.multi_level_conv_cls.1.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([3]).
        size mismatch for bbox_head.multi_level_conv_cls.2.weight: copying a param with shape torch.Size([80, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 128, 1, 1]).
        size mismatch for bbox_head.multi_level_conv_cls.2.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([3]).

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
3. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMCls.
4. The documentation has been modified accordingly, like docstring or example tutorials.

[okotaku]

I found it raised error when run test. I fixed it.

[RangiLyu]

LGTM