sc2bench.models.layer
Functions
|
Gets a layer module. |
|
Builds a bottleneck layer ResNet-based encoder and decoder (24 layers in total). |
|
Registers a layer class. |
|
Registers a function to build a layer module. |
Classes
|
An abstract class for entropy bottleneck-based layer. |
|
An entropy bottleneck layer as a simple CompressionModel in compressai. |
|
Factorized Prior(FP)-based encoder-decoder designed to create bottleneck for ResNet and variants. |
|
Mean-Scale Hyperprior(MSHP)-based bottleneck for ResNet and variants. |
|
Scale Hyperprior(SHP)-based bottleneck for ResNet and variants. |
|
Simple neural encoder-decoder that treats encoder's output as bottleneck. |