Shortcuts

mmedit.models.editors.dic.dic_net

Module Contents

Classes

DICNet

DIC network structure for face super-resolution.

FeedbackBlock

Feedback Block of DIC.

FeedbackBlockCustom

Custom feedback block, will be used as the first feedback block.

GroupResBlock

ResBlock with Group Conv.

FeatureHeatmapFusingBlock

Fusing Feature and Heatmap.

FeedbackBlockHeatmapAttention

Feedback block with HeatmapAttention.

class mmedit.models.editors.dic.dic_net.DICNet(in_channels, out_channels, mid_channels, num_blocks=6, hg_mid_channels=256, hg_num_keypoints=68, num_steps=4, upscale_factor=8, detach_attention=False, prelu_init=0.2, num_heatmaps=5, num_fusion_blocks=7)[source]

Bases: mmengine.model.BaseModule

DIC network structure for face super-resolution.

Paper: Deep Face Super-Resolution with Iterative Collaboration between

Attentive Recovery and Landmark Estimation

Parameters
  • in_channels (int) – Number of channels in the input image

  • out_channels (int) – Number of channels in the output image

  • mid_channels (int) – Channel number of intermediate features. Default: 64

  • num_blocks (tuple[int]) – Block numbers in the trunk network. Default: 6

  • hg_mid_channels (int) – Channel number of intermediate features of HourGlass. Default: 256

  • hg_num_keypoints (int) – Keypoint number of HourGlass. Default: 68

  • num_steps (int) – Number of iterative steps. Default: 4

  • upscale_factor (int) – Upsampling factor. Default: 8

  • detach_attention (bool) – Detached from the current tensor for heatmap or not.

  • prelu_init (float) – init of PReLU. Default: 0.2

  • num_heatmaps (int) – Number of heatmaps. Default: 5

  • num_fusion_blocks (int) – Number of fusion blocks. Default: 7

forward(x)[source]

Forward function.

Parameters

x (Tensor) – Input tensor.

Returns

Forward results. sr_outputs (list[Tensor]): forward sr results. heatmap_outputs (list[Tensor]): forward heatmap results.

Return type

Tensor

class mmedit.models.editors.dic.dic_net.FeedbackBlock(mid_channels, num_blocks, upscale_factor, padding=2, prelu_init=0.2)[source]

Bases: torch.nn.Module

Feedback Block of DIC.

It has a style of:

----- Module ----->
  ^            |
  |____________|
Parameters
  • mid_channels (int) – Number of channels in the intermediate features.

  • num_blocks (int) – Number of blocks.

  • upscale_factor (int) – upscale factor.

  • padding (int) – Padding size. Default: 2.

  • prelu_init (float) – init of PReLU. Default: 0.2

forward(x)[source]

Forward function.

Parameters

x (Tensor) – Input tensor with shape (n, c, h, w).

Returns

Forward results.

Return type

Tensor

class mmedit.models.editors.dic.dic_net.FeedbackBlockCustom(in_channels, mid_channels, num_blocks, upscale_factor)[source]

Bases: FeedbackBlock

Custom feedback block, will be used as the first feedback block.

Parameters
  • in_channels (int) – Number of channels in the input features.

  • mid_channels (int) – Number of channels in the intermediate features.

  • num_blocks (int) – Number of blocks.

  • upscale_factor (int) – upscale factor.

forward(x)[source]

Forward function.

Parameters

x (Tensor) – Input tensor with shape (n, c, h, w).

Returns

Forward results.

Return type

Tensor

class mmedit.models.editors.dic.dic_net.GroupResBlock(in_channels, out_channels, mid_channels, groups, res_scale=1.0)[source]

Bases: torch.nn.Module

ResBlock with Group Conv.

Parameters
  • in_channels (int) – Channel number of input features.

  • out_channels (int) – Channel number of output features.

  • mid_channels (int) – Channel number of intermediate features.

  • groups (int) – Number of blocked connections from input to output.

  • res_scale (float) – Used to scale the residual before addition. Default: 1.0.

forward(x)[source]

Forward function.

Parameters

x (Tensor) – Input tensor with shape (n, c, h, w).

Returns

Forward results.

Return type

Tensor

class mmedit.models.editors.dic.dic_net.FeatureHeatmapFusingBlock(in_channels, num_heatmaps, num_blocks, mid_channels=None)[source]

Bases: torch.nn.Module

Fusing Feature and Heatmap.

Parameters
  • in_channels (int) – Number of channels in the input features.

  • num_heatmaps (int) – Number of heatmap.

  • num_blocks (int) – Number of blocks.

  • mid_channels (int | None) – Number of channels in the intermediate features. Default: None

forward(feature, heatmap)[source]

Forward function.

Parameters
  • feature (Tensor) – Input feature tensor.

  • heatmap (Tensor) – Input heatmap tensor.

Returns

Forward results.

Return type

Tensor

class mmedit.models.editors.dic.dic_net.FeedbackBlockHeatmapAttention(mid_channels, num_blocks, upscale_factor, num_heatmaps, num_fusion_blocks, padding=2, prelu_init=0.2)[source]

Bases: FeedbackBlock

Feedback block with HeatmapAttention.

Parameters
  • in_channels (int) – Number of channels in the input features.

  • mid_channels (int) – Number of channels in the intermediate features.

  • num_blocks (int) – Number of blocks.

  • upscale_factor (int) – upscale factor.

  • padding (int) – Padding size. Default: 2.

  • prelu_init (float) – init of PReLU. Default: 0.2

forward(x, heatmap)[source]

Forward function.

Parameters
  • x (Tensor) – Input feature tensor.

  • heatmap (Tensor) – Input heatmap tensor.

Returns

Forward results.

Return type

Tensor

Read the Docs v: latest
Versions
master
latest
stable
zyh-re-docs
zyh-doc-notfound-extend
zyh-api-rendering
Downloads
pdf
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.