Shortcuts

mmedit.models.editors.aotgan.aot_encoder

Module Contents

Classes

AOTEncoder

Encoder used in AOT-GAN model.

class mmedit.models.editors.aotgan.aot_encoder.AOTEncoder(in_channels=4, mid_channels=64, out_channels=256, act_cfg=dict(type='ReLU'))[源代码]

Bases: mmengine.model.BaseModule

Encoder used in AOT-GAN model.

This implementation follows: Aggregated Contextual Transformations for High-Resolution Image Inpainting

参数
  • in_channels (int, optional) – Channel number of input feature. Default: 4.

  • mid_channels (int, optional) – Channel number of middle feature. Default: 64.

  • out_channels (int, optional) – Channel number of output feature. Default: 256.

  • act_cfg (dict, optional) – Config dict for activation layer, “relu” by default.

forward(x)[源代码]

Forward Function.

参数

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

返回

Output tensor with shape of (n, c, h’, w’).

返回类型

Tensor

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

Free document hosting provided by Read the Docs.