spandrel.architectures.ESRGAN.ESRGAN

class documentation

class ESRGAN(nn.Module): (source)

Constructor: ESRGAN(in_nc, out_nc, num_filters, num_blocks, ...)

View In Hierarchy

Undocumented

Method __init__ ESRGAN - Enhanced Super-Resolution Generative Adversarial Networks. By Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, and Chen Change Loy. This is old-arch Residual in Residual Dense Block Network and is not the newest revision that's available at github...
Method forward Undocumented
Class Variable hyperparameters Undocumented
Instance Variable model Undocumented
Instance Variable scale Undocumented
Instance Variable shuffle_factor Undocumented
def __init__(self, *, in_nc: int = 3, out_nc: int = 3, num_filters: int = 64, num_blocks: int = 23, scale: int = 4, plus: bool = False, shuffle_factor: int|None = None, norm=None, act: str = 'leakyrelu', upsampler: str = 'upconv', mode: B.ConvMode = 'CNA'): (source)

ESRGAN - Enhanced Super-Resolution Generative Adversarial Networks. By Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, and Chen Change Loy. This is old-arch Residual in Residual Dense Block Network and is not the newest revision that's available at github.com/xinntao/ESRGAN. This is on purpose, the newest Network has severely limited the potential use of the Network with no benefits. This network supports model files from both new and old-arch.

Parameters
in_nc:intUndocumented
out_nc:intUndocumented
num_filters:intUndocumented
num_blocks:intUndocumented
scale:intUndocumented
plus:boolUndocumented
shuffle_factor:int|NoneUndocumented
normNormalization layer
act:strActivation layer
upsampler:strUpsample layer. upconv, pixel_shuffle
mode:B.ConvModeConvolution mode
def forward(self, x): (source)

Undocumented

hyperparameters: dict = (source)

Undocumented

model = (source)

Undocumented

scale = (source)

Undocumented

shuffle_factor = (source)

Undocumented