HRNet

class mmpretrain.models.backbones.HRNet(arch='w32', extra=None, in_channels=3, conv_cfg=None, norm_cfg={'type': 'BN'}, norm_eval=False, with_cp=False, zero_init_residual=False, multiscale_output=True, init_cfg=[{'type': 'Kaiming', 'layer': 'Conv2d'}, {'type': 'Constant', 'val': 1, 'layer': ['_BatchNorm', 'GroupNorm']}])

HRNet backbone.

High-Resolution Representations for Labeling Pixels and Regions.

Parameters:

• arch (str) – The preset HRNet architecture, includes ‘w18’, ‘w30’, ‘w32’, ‘w40’, ‘w44’, ‘w48’, ‘w64’. It will only be used if extra is None. Defaults to ‘w32’.

• extra (dict, optional) –

  Detailed configuration for each stage of HRNet. There must be 4 stages, the configuration for each stage must have 5 keys:

  • num_modules (int): The number of HRModule in this stage.

  • num_branches (int): The number of branches in the HRModule.

  • block (str): The type of convolution block. Please choose between ‘BOTTLENECK’ and ‘BASIC’.

  • num_blocks (tuple): The number of blocks in each branch. The length must be equal to num_branches.

  • num_channels (tuple): The number of base channels in each branch. The length must be equal to num_branches.

  Defaults to None.

• in_channels (int) – Number of input image channels. Defaults to 3.

• conv_cfg (dict, optional) – Dictionary to construct and config conv layer. Defaults to None.

• norm_cfg (dict) – Dictionary to construct and config norm layer. Defaults to dict(type='BN').

• norm_eval (bool) – Whether to set norm layers to eval mode, namely, freeze running stats (mean and var). Note: Effect on Batch Norm and its variants only. Defaults to False.

• with_cp (bool) – Use checkpoint or not. Using checkpoint will save some memory while slowing down the training speed. Defaults to False.

• zero_init_residual (bool) – Whether to use zero init for last norm layer in resblocks to let them behave as identity. Defaults to False.

• multiscale_output (bool) – Whether to output multi-level features produced by multiple branches. If False, only the first level feature will be output. Defaults to True.

• init_cfg (dict or list[dict], optional) – Initialization config dict. Defaults to None.

Example

>>> import torch
>>> from mmpretrain.models import HRNet
>>> extra = dict(
>>>     stage1=dict(
>>>         num_modules=1,
>>>         num_branches=1,
>>>         block='BOTTLENECK',
>>>         num_blocks=(4, ),
>>>         num_channels=(64, )),
>>>     stage2=dict(
>>>         num_modules=1,
>>>         num_branches=2,
>>>         block='BASIC',
>>>         num_blocks=(4, 4),
>>>         num_channels=(32, 64)),
>>>     stage3=dict(
>>>         num_modules=4,
>>>         num_branches=3,
>>>         block='BASIC',
>>>         num_blocks=(4, 4, 4),
>>>         num_channels=(32, 64, 128)),
>>>     stage4=dict(
>>>         num_modules=3,
>>>         num_branches=4,
>>>         block='BASIC',
>>>         num_blocks=(4, 4, 4, 4),
>>>         num_channels=(32, 64, 128, 256)))
>>> self = HRNet(extra, in_channels=1)
>>> self.eval()
>>> inputs = torch.rand(1, 1, 32, 32)
>>> level_outputs = self.forward(inputs)
>>> for level_out in level_outputs:
...     print(tuple(level_out.shape))
(1, 32, 8, 8)
(1, 64, 4, 4)
(1, 128, 2, 2)
(1, 256, 1, 1)

forward(x)

Forward function.

property norm1

the normalization layer named “norm1”

Type:

nn.Module

property norm2

the normalization layer named “norm2”

Type:

nn.Module

train(mode=True)

Convert the model into training mode will keeping the normalization layer freezed.