[Feature] enhance swin pretrained model loading (#3097)

Thanks for your contribution and we appreciate it a lot. The following
instructions would make your pull request more healthy and more easily
get feedback. If you do not understand some items, don't worry, just
make the pull request and seek help from maintainers.

## Motivation

Enhance pretrained SwinTransformer loading when setting non-standard
backbone `depths`.

## Modification

Enhance pretrained SwinTransformer loading when setting non-standard
backbone `depths`.

## BC-breaking (Optional)

Does the modification introduce changes that break the
backward-compatibility of the downstream repos?
If so, please describe how it breaks the compatibility and how the
downstream projects should modify their code to keep compatibility with
this PR.

## Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases
here, and update the documentation.

## 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
MMDet3D.
4. The documentation has been modified accordingly, like docstring or
example tutorials.

---------

Co-authored-by: SheffieldCao <[email protected]>

mmseg/models/backbones/swin.py

@@ -716,20 +716,22 @@ def init_weights(self):
             ]
             for table_key in relative_position_bias_table_keys:
                 table_pretrained = state_dict[table_key]
-                table_current = self.state_dict()[table_key]
-                L1, nH1 = table_pretrained.size()
-                L2, nH2 = table_current.size()
-                if nH1 != nH2:
-                    print_log(f'Error in loading {table_key}, pass')
-                elif L1 != L2:
-                    S1 = int(L1**0.5)
-                    S2 = int(L2**0.5)
-                    table_pretrained_resized = F.interpolate(
-                        table_pretrained.permute(1, 0).reshape(1, nH1, S1, S1),
-                        size=(S2, S2),
-                        mode='bicubic')
-                    state_dict[table_key] = table_pretrained_resized.view(
-                        nH2, L2).permute(1, 0).contiguous()
+                if table_key in self.state_dict():
+                    table_current = self.state_dict()[table_key]
+                    L1, nH1 = table_pretrained.size()
+                    L2, nH2 = table_current.size()
+                    if nH1 != nH2:
+                        print_log(f'Error in loading {table_key}, pass')
+                    elif L1 != L2:
+                        S1 = int(L1**0.5)
+                        S2 = int(L2**0.5)
+                        table_pretrained_resized = F.interpolate(
+                            table_pretrained.permute(1, 0).reshape(
+                                1, nH1, S1, S1),
+                            size=(S2, S2),
+                            mode='bicubic')
+                        state_dict[table_key] = table_pretrained_resized.view(
+                            nH2, L2).permute(1, 0).contiguous()
 
             # load state_dict
             self.load_state_dict(state_dict, strict=False)