mmagic.models.archs.resnet

Module Contents

Classes

BasicBlock	Basic block for ResNet.
Bottleneck	Bottleneck block for ResNet.
ResNet	General ResNet.

class mmagic.models.archs.resnet.BasicBlock(inplanes: int, planes: int, stride: int = 1, dilation: int = 1, downsample: Optional[torch.nn.Module] = None, act_cfg: dict = dict(type='ReLU'), conv_cfg: Optional[dict] = None, norm_cfg: dict = dict(type='BN'), with_cp: bool = False)

Bases: torch.nn.Module

Basic block for ResNet.

Parameters

• inplanes (int) – Number of input channels.

• planes (int) – Number of output channels.

• stride (int) – Stride of the first block of one stage. Default: 1.

• dilation (int) – Dilation of one stage. Default: 1.

• downsample (nn.Module) – Downsample module. Default: None.

• act_cfg (dict) – Dictionary to construct and config activation layer. Default: dict(type=’ReLU’).

• conv_cfg (dict) – Dictionary to construct and config convolution layer. Default: None.

• norm_cfg (dict) – Dictionary to construct and config norm layer. Default: dict(type=’BN’).

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

property norm1: torch.nn.Module

normalization layer after the first convolution layer

Type

nn.Module

property norm2: torch.nn.Module

normalization layer after the second convolution layer

Type

nn.Module

expansion = 1

forward(x: torch.Tensor) → torch.Tensor

Forward function.

class mmagic.models.archs.resnet.Bottleneck(inplanes: int, planes: int, stride: int = 1, dilation: int = 1, downsample: Optional[torch.nn.Module] = None, act_cfg: dict = dict(type='ReLU'), conv_cfg: Optional[dict] = None, norm_cfg: dict = dict(type='BN'), with_cp: bool = False)

Bases: torch.nn.Module

Bottleneck block for ResNet.

Parameters

• inplanes (int) – Number of input channels.

• planes (int) – Number of output channels.

• stride (int) – Stride of the first block of one stage. Default: 1.

• dilation (int) – Dilation of one stage. Default: 1.

• downsample (nn.Module) – Downsample module. Default: None.

• act_cfg (dict) – Dictionary to construct and config activation layer. Default: dict(type=’ReLU’).

• conv_cfg (dict) – Dictionary to construct and config convolution layer. Default: None.

• norm_cfg (dict) – Dictionary to construct and config norm layer. Default: dict(type=’BN’).

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

property norm1: torch.nn.Module

normalization layer after the first convolution layer

Type

nn.Module

property norm2: torch.nn.Module

normalization layer after the second convolution layer

Type

nn.Module

property norm3: torch.nn.Module

normalization layer after the second convolution layer

Type

nn.Module

expansion = 4

forward(x: torch.Tensor) → torch.Tensor

class mmagic.models.archs.resnet.ResNet(depth: int, in_channels: int = 3, stem_channels: int = 64, base_channels: int = 64, num_stages: int = 4, strides: Sequence[int] = (1, 2, 2, 2), dilations: Sequence[int] = (1, 1, 2, 4), deep_stem: bool = False, avg_down: bool = False, frozen_stages: int = - 1, act_cfg: dict = dict(type='ReLU'), conv_cfg: Optional[dict] = None, norm_cfg: dict = dict(type='BN'), with_cp: bool = False, multi_grid: Optional[Sequence[int]] = None, contract_dilation: bool = False, zero_init_residual: bool = True)

Bases: torch.nn.Module

General ResNet.

This class is adopted from https://github.com/open-mmlab/mmsegmentation/blob/master/mmseg/models/backbones/resnet.py.

Parameters

• depth (int) – Depth of resnet, from {18, 34, 50, 101, 152}.

• in_channels (int) – Number of input image channels. Default” 3.

• stem_channels (int) – Number of stem channels. Default: 64.

• base_channels (int) – Number of base channels of res layer. Default: 64.

• num_stages (int) – Resnet stages, normally 4.

• strides (Sequence[int]) – Strides of the first block of each stage. Default: (1, 2, 2, 2).

• dilations (Sequence[int]) – Dilation of each stage. Default: (1, 1, 2, 4).

• deep_stem (bool) – Replace 7x7 conv in input stem with 3 3x3 conv. Default: False.

• avg_down (bool) – Use AvgPool instead of stride conv when downsampling in the bottleneck. Default: False.

• frozen_stages (int) – Stages to be frozen (stop grad and set eval mode). -1 means not freezing any parameters. Default: -1.

• act_cfg (dict) – Dictionary to construct and config activation layer. Default: dict(type=’ReLU’).

• conv_cfg (dict) – Dictionary to construct and config convolution layer. Default: None.

• norm_cfg (dict) – Dictionary to construct and config norm layer. Default: dict(type=’BN’).

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

• multi_grid (Sequence[int]|None) – Multi grid dilation rates of last stage. Default: None.

• contract_dilation (bool) – Whether contract first dilation of each layer Default: False.

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

property norm1: torch.nn.Module

normalization layer after the second convolution layer

Type

nn.Module

arch_settings

_make_stem_layer(in_channels: int, stem_channels: int) → None

Make stem layer for ResNet.

_make_layer(block: BasicBlock, planes: int, blocks: int, stride: int = 1, dilation: int = 1) → torch.nn.Module

_nostride_dilate(m: torch.nn.Module, dilate: int) → None

init_weights(pretrained: Optional[str] = None) → None

Init weights for the model.

Parameters

pretrained (str, optional) – Path for pretrained weights. If given None, pretrained weights will not be loaded. Defaults to None.

_freeze_stages() → None

Freeze stages param and norm stats.

forward(x: torch.Tensor) → List[torch.Tensor]

Forward function.

Parameters

x (Tensor) – Input tensor with shape (N, C, H, W).

Returns

Output tensor.

Return type

Tensor