`mmagic.models.editors.gca.resgca_enc`¶

Module Contents¶

Classes¶

`BasicBlock`	Basic residual block.
`ResNetEnc`	ResNet encoder for image matting.
`ResShortcutEnc`	ResNet backbone for image matting with shortcut connection.
`ResGCAEncoder`	ResNet backbone with shortcut connection and gca module.

class mmagic.models.editors.gca.resgca_enc.BasicBlock(in_channels, out_channels, kernel_size=3, stride=1, interpolation=None, conv_cfg=None, norm_cfg=dict(type='BN'), act_cfg=dict(type='ReLU'), with_spectral_norm=False)[source]¶

Bases: torch.nn.Module

Basic residual block.

Parameters

in_channels (int) – Input channels of the block.
out_channels (int) – Output channels of the block.
kernel_size (int) – Kernel size of the convolution layers. Default: 3.
stride (int) – Stride of the first conv of the block. Default: 1.
interpolation (nn.Module, optional) – Interpolation module for skip connection. Default: None.
conv_cfg (dict) – dictionary to construct convolution layer. If it is None, 2d convolution will be applied. Default: None.
norm_cfg (dict) – Config dict for normalization layer. “BN” by default.
act_cfg (dict) – Config dict for activation layer, “ReLU” by default.
with_spectral_norm (bool) – Whether use spectral norm after conv. Default: False.

expansion = 1[source]¶

build_conv1(in_channels, out_channels, kernel_size, stride, conv_cfg, norm_cfg, act_cfg, with_spectral_norm)[source]¶

Build conv1 of the block.

Parameters

in_channels (int) – The input channels of the ConvModule.
out_channels (int) – The output channels of the ConvModule.
kernel_size (int) – The kernel size of the ConvModule.
stride (int) – The stride of the ConvModule. If stride is set to 2, then conv_cfg will be overwritten as dict(type='Deconv') and kernel_size will be overwritten as 4.
conv_cfg (dict) – The conv config of the ConvModule.
norm_cfg (dict) – The norm config of the ConvModule.
act_cfg (dict) – The activation config of the ConvModule.
with_spectral_norm (bool) – Whether use spectral norm.

Returns

The built ConvModule.

Return type

nn.Module

build_conv2(in_channels, out_channels, kernel_size, conv_cfg, norm_cfg, with_spectral_norm)[source]¶

Build conv2 of the block.

Parameters

in_channels (int) – The input channels of the ConvModule.
out_channels (int) – The output channels of the ConvModule.
kernel_size (int) – The kernel size of the ConvModule.
stride (int) – The stride of the ConvModule. If stride is set to 2, then conv_cfg will be overwritten as dict(type='Deconv') and kernel_size will be overwritten as 4.
conv_cfg (dict) – The conv config of the ConvModule.
norm_cfg (dict) – The norm config of the ConvModule.
act_cfg (dict) – The activation config of the ConvModule.
with_spectral_norm (bool) – Whether use spectral norm.

Returns

The built ConvModule.

Return type

nn.Module

forward(x)[source]¶

Forward function.

Parameters: inputs (torch.Tensor) – Input tensor.
Returns: Output tensor.
Return type: Tensor

class mmagic.models.editors.gca.resgca_enc.ResNetEnc(block, layers, in_channels, conv_cfg=None, norm_cfg=dict(type='BN'), act_cfg=dict(type='ReLU'), with_spectral_norm=False, late_downsample=False, init_cfg: Optional[dict] = None)[source]¶

Bases: mmengine.model.BaseModule

ResNet encoder for image matting.

This class is adopted from https://github.com/Yaoyi-Li/GCA-Matting. Implement and pre-train on ImageNet with the tricks from https://arxiv.org/abs/1812.01187 without the mix-up part.

Parameters

block (str) – Type of residual block. Currently only BasicBlock is implemented.
layers (list[int]) – Number of layers in each block.
in_channels (int) – Number of input channels.
conv_cfg (dict) – dictionary to construct convolution layer. If it is None, 2d convolution will be applied. Default: None.
norm_cfg (dict) – Config dict for normalization layer. “BN” by default.
act_cfg (dict) – Config dict for activation layer, “ReLU” by default.
with_spectral_norm (bool) – Whether use spectral norm after conv. Default: False.
late_downsample (bool) – Whether to adopt late downsample strategy, Default: False.
init_cfg (dict, optional) – Initialization config dict. Default: None.

init_weights()[source]¶: Init weights for the module.

_make_layer(block, planes, num_blocks, stride, conv_cfg, norm_cfg, act_cfg, with_spectral_norm)[source]¶

forward(x)[source]¶

Forward function.

Parameters: x (Tensor) – Input tensor with shape (N, C, H, W).
Returns: Output tensor.
Return type: Tensor

class mmagic.models.editors.gca.resgca_enc.ResShortcutEnc(block, layers, in_channels, conv_cfg=None, norm_cfg=dict(type='BN'), act_cfg=dict(type='ReLU'), with_spectral_norm=False, late_downsample=False, order=('conv', 'act', 'norm'), init_cfg: Optional[dict] = None)[source]¶

Bases: ResNetEnc

ResNet backbone for image matting with shortcut connection.

image ---------------- shortcut[0] --- feat1
  |
conv1-conv2 ---------- shortcut[1] --- feat2
       |
      conv3-layer1 --- shortcut[2] --- feat3
              |
             layer2 -- shortcut[4] --- feat4
               |
              layer3 - shortcut[5] --- feat5
                |
               layer4 ---------------- out

Baseline model of Natural Image Matting via Guided Contextual Attention https://arxiv.org/pdf/2001.04069.pdf.

Parameters

block (str) – Type of residual block. Currently only BasicBlock is implemented.
layers (list[int]) – Number of layers in each block.
in_channels (int) – Number of input channels.
conv_cfg (dict) – Dictionary to construct convolution layer. If it is None, 2d convolution will be applied. Default: None.
norm_cfg (dict) – Config dict for normalization layer. “BN” by default.
act_cfg (dict) – Config dict for activation layer, “ReLU” by default.
with_spectral_norm (bool) – Whether use spectral norm after conv. Default: False.
late_downsample (bool) – Whether to adopt late downsample strategy. Default: False.
order (tuple[str]) – Order of conv, norm and act layer in shortcut convolution module. Default: (‘conv’, ‘act’, ‘norm’).
init_cfg (dict, optional) – Initialization config dict. Default: None.

_make_shortcut(in_channels, out_channels, conv_cfg, norm_cfg, act_cfg, order, with_spectral_norm)[source]¶

forward(x)[source]¶

Forward function.

Parameters: x (Tensor) – Input tensor with shape (N, C, H, W).
Returns: Contains the output tensor and shortcut feature.
Return type: dict

class mmagic.models.editors.gca.resgca_enc.ResGCAEncoder(block, layers, in_channels, conv_cfg=None, norm_cfg=dict(type='BN'), act_cfg=dict(type='ReLU'), with_spectral_norm=False, late_downsample=False, order=('conv', 'act', 'norm'), init_cfg: Optional[dict] = None)[source]¶

Bases: ResShortcutEnc

ResNet backbone with shortcut connection and gca module.

image ---------------- shortcut[0] -------------- feat1
 |
conv1-conv2 ---------- shortcut[1] -------------- feat2
       |
     conv3-layer1 ---- shortcut[2] -------------- feat3
             |
             | image - guidance_conv ------------ img_feat
             |             |
            layer2 --- gca_module - shortcut[4] - feat4
                            |
                          layer3 -- shortcut[5] - feat5
                             |
                           layer4 --------------- out

gca module also requires unknown tensor generated by trimap which is ignored in the above graph.

Implementation of Natural Image Matting via Guided Contextual Attention https://arxiv.org/pdf/2001.04069.pdf.

Parameters

block (str) – Type of residual block. Currently only BasicBlock is implemented.
layers (list[int]) – Number of layers in each block.
in_channels (int) – Number of input channels.
conv_cfg (dict) – Dictionary to construct convolution layer. If it is None, 2d convolution will be applied. Default: None.
norm_cfg (dict) – Config dict for normalization layer. “BN” by default.
act_cfg (dict) – Config dict for activation layer, “ReLU” by default.
late_downsample (bool) – Whether to adopt late downsample strategy. Default: False.
order (tuple[str]) – Order of conv, norm and act layer in shortcut convolution module. Default: (‘conv’, ‘act’, ‘norm’).
init_cfg (dict, optional) – Initialization config dict. Default: None.

forward(x)[source]¶

Forward function.

Parameters: x (Tensor) – Input tensor with shape (N, C, H, W).
Returns: Contains the output tensor, shortcut feature and intermediate feature.
Return type: dict

mmagic.models.editors.gca.resgca_enc¶

Module Contents¶

Classes¶

`mmagic.models.editors.gca.resgca_enc`¶