[Feature] Add DOLG neck for image retrieval

[zzc98]

Motivation

The implementation of DOLG, which is a kind of neck network in the retrieval task. More details about DOLG can be found in DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features.

Use cases

model = dict(
    type='ImageClassifier',
    backbone=dict(
        type='ResNet',
        depth=101,
        num_stages=4,
        out_indices=(2, 3,),
        style='pytorch'
    ),
    neck=dict(type='DOLG',
               local_dim=1024,     # feature dim in last second stage (local feat)
               global_dim=2048,  # feature dim in last stage (global feat)
               out_dim=2048, 
               dilation_rates=(3, 6, 9)
    ),
    head=dict(
        type='LinearClsHead',
        num_classes=1000,
        in_channels=2048,
        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
        topk=(1, 5),
    ),
)

Checklist

Before PR:

• Pre-commit or other linting tools are used to fix the potential lint issues.
• Bug fixes are fully covered by unit tests, the case that causes the bug should be added in the unit tests.
• The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
• The documentation has been modified accordingly, like docstring or example tutorials.

After PR:

• If the modification has potential influence on downstream or other related projects, this PR should be tested with those projects, like MMDet or MMSeg.
• CLA has been signed and all committers have signed the CLA in this PR.

[codecov]

Codecov Report

Patch coverage has no change and project coverage change: +86.85 🎉

Comparison is base (b8b31e9) 0.02% compared to head (a59f588) 86.88%.

❗ Current head a59f588 differs from pull request most recent head 3e16369. Consider uploading reports for the commit 3e16369 to get more accurate results

Additional details and impacted files

@@             Coverage Diff              @@
##           dev-1.x    #1053       +/-   ##
============================================
+ Coverage     0.02%   86.88%   +86.85%     
============================================
  Files          121      170       +49     
  Lines         8217    14056     +5839     
  Branches      1368     2225      +857     
============================================
+ Hits             2    12212    +12210     
+ Misses        8215     1461     -6754     
- Partials         0      383      +383     

Flag	Coverage Δ
unittests	86.88% <ø> (+86.85%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
mmcls/datasets/transforms/compose.py
mmcls/models/backbones/davit.py	84.94% <0.00%> (ø)
mmcls/models/classifiers/timm.py	25.97% <0.00%> (ø)
mmcls/models/retrievers/__init__.py	100.00% <0.00%> (ø)
mmcls/engine/hooks/margin_head_hooks.py	92.59% <0.00%> (ø)
mmcls/engine/hooks/ema_hook.py	81.69% <0.00%> (ø)
mmcls/apis/model.py	88.17% <0.00%> (ø)
mmcls/models/utils/layer_scale.py	86.66% <0.00%> (ø)
mmcls/evaluation/metrics/retrieval.py	84.70% <0.00%> (ø)
mmcls/models/necks/reduction.py	100.00% <0.00%> (ø)
... and 161 more

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report at Codecov.
📢 Do you have feedback about the report comment? Let us know in this issue.

[okotaku]

I understand. LGTM

[Ezra-Yu]

LGTM.