swin_transformer_v2: missing keys in souce state_dict

[lzj1214]

使用swin_transformer_v2时候会提示missing keys（目前测了tiny和small），转onnx也失败。训练是正常的

python tools/single_test.py ../../7X_hotspot.jpg models/swin_transformer_v2/tiny_256.py --classes-map datas/imageNet1kAnnotation.txt
/anaconda3/envs/iqa/lib/python3.10/site-packages/torch/functional.py:513: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3609.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
Loading swinv2-tiny-w16_3rdparty_in1k-256px_20220803-9651cdd7.pth
/Awesome-Backbones/utils/checkpoint.py:218: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  checkpoint = torch.load(filename, map_location)
The model and loaded state dict do not match exactly

missing keys in source state_dict: backbone.stages.0.blocks.0.attn.w_msa.relative_coords_table, backbone.stages.0.blocks.0.attn.w_msa.relative_position_index, backbone.stages.0.blocks.1.attn.w_msa.relative_coords_table, backbone.stages.0.blocks.1.attn.w_msa.relative_position_index, backbone.stages.1.blocks.0.attn.w_msa.relative_coords_table, backbone.stages.1.blocks.0.attn.w_msa.relative_position_index, backbone.stages.1.blocks.1.attn.w_msa.relative_coords_table, backbone.stages.1.blocks.1.attn.w_msa.relative_position_index, backbone.stages.2.blocks.0.attn.w_msa.relative_coords_table, backbone.stages.2.blocks.0.attn.w_msa.relative_position_index, backbone.stages.2.blocks.1.attn.w_msa.relative_coords_table, backbone.stages.2.blocks.1.attn.w_msa.relative_position_index, backbone.stages.2.blocks.2.attn.w_msa.relative_coords_table, backbone.stages.2.blocks.2.attn.w_msa.relative_position_index, backbone.stages.2.blocks.3.attn.w_msa.relative_coords_table, backbone.stages.2.blocks.3.attn.w_msa.relative_position_index, backbone.stages.2.blocks.4.attn.w_msa.relative_coords_table, backbone.stages.2.blocks.4.attn.w_msa.relative_position_index, backbone.stages.2.blocks.5.attn.w_msa.relative_coords_table, backbone.stages.2.blocks.5.attn.w_msa.relative_position_index, backbone.stages.3.blocks.0.attn.w_msa.relative_coords_table, backbone.stages.3.blocks.0.attn.w_msa.relative_position_index, backbone.stages.3.blocks.1.attn.w_msa.relative_coords_table, backbone.stages.3.blocks.1.attn.w_msa.relative_position_index

{'pred_label': 404, 'pred_score': 8.37266731262207, 'pred_class': 'airliner'}