Shortcuts

mmedit.models.editors.nafnet.nafnet_net

Module Contents

Classes

NAFNet

NAFNet.

NAFNetLocal

The original version of NAFNetLocal in "Simple Baseline for Image

NAFBlock

NAFNet's Block in paper.

SimpleGate

The Simple Gate in "Simple Baseline for Image Restoration".

class mmedit.models.editors.nafnet.nafnet_net.NAFNet(img_channel=3, mid_channels=16, middle_blk_num=1, enc_blk_nums=[], dec_blk_nums=[])[source]

Bases: mmengine.model.BaseModule

NAFNet.

The original version of NAFNet in “Simple Baseline for Image Restoration”.

Parameters
  • img_channels (int) – Channel number of inputs.

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

  • middle_blk_num (int) – Number of middle blocks.

  • enc_blk_nums (List of int) – Number of blocks for each encoder.

  • dec_blk_nums (List of int) – Number of blocks for each decoder.

forward(inp)[source]

Forward function.

Parameters

inp – input tensor image with (B, C, H, W) shape

check_image_size(x)[source]

Check image size and pad images so that it has enough dimension do downsample.

Parameters

x – input tensor image with (B, C, H, W) shape.

class mmedit.models.editors.nafnet.nafnet_net.NAFNetLocal(*args, train_size=(1, 3, 256, 256), fast_imp=False, **kwargs)[source]

Bases: mmedit.models.editors.nafnet.naf_avgpool2d.Local_Base, NAFNet

The original version of NAFNetLocal in “Simple Baseline for Image Restoration”.

NAFNetLocal uses local average pooling modules than NAFNet.

Parameters
  • img_channels (int) – Channel number of inputs.

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

  • middle_blk_num (int) – Number of middle blocks.

  • enc_blk_nums (List of int) – Number of blocks for each encoder.

  • dec_blk_nums (List of int) – Number of blocks for each decoder.

class mmedit.models.editors.nafnet.nafnet_net.NAFBlock(in_channels, DW_Expand=2, FFN_Expand=2, drop_out_rate=0.0)[source]

Bases: mmengine.model.BaseModule

NAFNet’s Block in paper.

Simple gate will shrink the channel to a half. To keep the number of channels, it expands the channels first.

Parameters
  • in_channels (int) – number of channels

  • DW_Expand (int) – channel expansion factor for part 1

  • FFN_Expand (int) – channel expansion factor for part 2

  • drop_out_rate (float) – drop out ratio

forward(inp)[source]

Forward Function.

Parameters

inp – input tensor image

class mmedit.models.editors.nafnet.nafnet_net.SimpleGate(init_cfg: Union[dict, List[dict], None] = None)[source]

Bases: mmengine.model.BaseModule

The Simple Gate in “Simple Baseline for Image Restoration”.

Parameters

x – input tensor feature map with (B, 2 * C, H, W)

Returns

x1 * x2 (where x1, x2 are two separate parts by simple split x to [B, C, H, W])

forward(x)[source]
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.