Motivation

In some cases, it is necessary to reduce the dimension of extracted feature, so Reduction is implemented in necks.

Use cases

model = dict(
    type='ImageClassifier',
    backbone=dict(
        type='ResNet',
        depth=101,
        num_stages=4,
        out_indices=(3,),
        style='pytorch'
    ),
    neck=[
        dict(type='GeneralizedMeanPooling'),
        dict(type='LinearReduction',
             in_channels=2048,
             out_channels=512,
             act_cfg=dict(type='ReLU'),
             norm_cfg=dict(type='BN1d')
             )
    ],
    head=dict(
        type='LinearClsHead',
        num_classes=1000,
        in_channels=512,
        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.