HRFuseScales¶

class mmpretrain.models.necks.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)).