basicsr.archs.hifacegan_util¶
- class basicsr.archs.hifacegan_util.BaseNetwork[source]¶
Bases:
Module
A basis for hifacegan archs with custom initialization
- forward(x)[source]¶
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
- training: bool¶
- class basicsr.archs.hifacegan_util.LIPEncoder(input_nc, ngf, sw, sh, n_2xdown, norm_layer=<class 'torch.nn.modules.instancenorm.InstanceNorm2d'>)[source]¶
Bases:
BaseNetwork
Local Importance-based Pooling (Ziteng Gao et.al.,ICCV 2019)
- forward(x)[source]¶
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
- training: bool¶
- class basicsr.archs.hifacegan_util.SPADE(config_text, norm_nc, label_nc)[source]¶
Bases:
Module
- forward(x, segmap)[source]¶
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
- training: bool¶
- class basicsr.archs.hifacegan_util.SPADEResnetBlock(fin, fout, norm_g='spectralspadesyncbatch3x3', semantic_nc=3)[source]¶
Bases:
Module
ResNet block that uses SPADE. It differs from the ResNet block of pix2pixHD in that it takes in the segmentation map as input, learns the skip connection if necessary, and applies normalization first and then convolution. This architecture seemed like a standard architecture for unconditional or class-conditional GAN architecture using residual block. The code was inspired from https://github.com/LMescheder/GAN_stability.
- forward(x, seg)[source]¶
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
- training: bool¶
- class basicsr.archs.hifacegan_util.SimplifiedLIP(channels)[source]¶
Bases:
Module
- forward(x)[source]¶
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
- training: bool¶
- class basicsr.archs.hifacegan_util.SoftGate[source]¶
Bases:
Module
- COEFF = 12.0¶
- forward(x)[source]¶
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
- training: bool¶