sc2bench.models.backbone

Functions

check_if_updatable(model)	Checks if the given model is updatable.
get_backbone(cls_or_func_name, **kwargs)	Gets a backbone model.
register_backbone_class(cls)	Registers a backbone model (usually a classification model).
register_backbone_func(func)	Registers a function to build a backbone model (usually a classification model).
splittable_hybrid_vit(bottleneck_config[, ...])	Builds Hybrid ViT-based splittable image classification model containing neural encoder, entropy bottleneck, and decoder.
splittable_regnet(bottleneck_config[, ...])	Builds RegNet-based splittable image classification model containing neural encoder, entropy bottleneck, and decoder.
splittable_resnest(bottleneck_config[, ...])	Builds ResNeSt-based splittable image classification model containing neural encoder, entropy bottleneck, and decoder.
splittable_resnet(bottleneck_config[, ...])	Builds ResNet-based splittable image classification model containing neural encoder, entropy bottleneck, and decoder.

Classes

FeatureExtractionBackbone(model, ...[, ...])	A feature extraction-based backbone model.
SplittableHybridViT(bottleneck_layer, ...[, ...])	Hybrid ViT-based splittable image classification model containing neural encoder, entropy bottleneck, and decoder.
SplittableRegNet(bottleneck_layer, regnet_model)	RegNet-based splittable image classification model containing neural encoder, entropy bottleneck, and decoder.
SplittableResNet(bottleneck_layer, resnet_model)	ResNet/ResNeSt-based splittable image classification model containing neural encoder, entropy bottleneck, and decoder.
UpdatableBackbone([analyzer_configs])	A base, updatable R-CNN model.