Note

You are reading the documentation for MMClassification 0.x, which will soon be deprecated at the end of 2022. We recommend you upgrade to MMClassification 1.0 to enjoy fruitful new features and better performance brought by OpenMMLab 2.0. Check the installation tutorial, migration tutorial and changelog for more details.

HRFuseScales¶

class mmcls.models.HRFuseScales(in_channels, out_channels=2048, norm_cfg={'momentum': 0.1, 'type': 'BN'}, init_cfg={'layer': 'Linear', 'std': 0.01, 'type': 'Normal'})[source]¶

Fuse feature map of multiple scales in HRNet.

Parameters

in_channels (list[int]) – The input channels of all scales.
out_channels (int) – The channels of fused feature map. Defaults to 2048.
norm_cfg (dict) – dictionary to construct norm layers. Defaults to dict(type='BN', momentum=0.1).
init_cfg (dict | list[dict], optional) – Initialization config dict. Defaults to dict(type='Normal', layer='Linear', std=0.01)).

forward(x)[source]¶

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.