sc2bench.models.layer

Functions

get_layer(cls_or_func_name, **kwargs)

Gets a layer module.

larger_resnet_bottleneck([...])

Builds a bottleneck layer ResNet-based encoder and decoder (24 layers in total).

register_layer_class(cls)

Registers a layer class.

register_layer_func(func)

Registers a function to build a layer module.

Classes

BaseBottleneck(entropy_bottleneck_channels)

An abstract class for entropy bottleneck-based layer.

EntropyBottleneckLayer(**kwargs)

An entropy bottleneck layer as a simple CompressionModel in compressai.

FPBasedResNetBottleneck([...])

Factorized Prior(FP)-based encoder-decoder designed to create bottleneck for ResNet and variants.

MSHPBasedResNetBottleneck([...])

Mean-Scale Hyperprior(MSHP)-based bottleneck for ResNet and variants.

SHPBasedResNetBottleneck([...])

Scale Hyperprior(SHP)-based bottleneck for ResNet and variants.

SimpleBottleneck(encoder, decoder[, ...])

Simple neural encoder-decoder that treats encoder's output as bottleneck.