sparsezoo.models.detection package

Submodules

sparsezoo.models.detection.ssd module

SSD models:

https://arxiv.org/abs/1512.02325

sparsezoo.models.detection.ssd.ssd_resnet50_300(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'coco', training_scheme: Optional[str] = None, sparse_name: str = 'base', sparse_category: str = 'none', sparse_target: Optional[str] = None, override_folder_name: Optional[str] = None, override_parent_path: Optional[str] = None, force_token_refresh: bool = False) → sparsezoo.objects.model.Model[source]

Convenience function for getting an ssd resnet50 300 model

Parameters

  • framework – The framework the model the object belongs to was trained on; e.g. pytorch, tensorflow

  • repo – the source repo for the model the object belongs to; e.g. sparseml, torchvision

  • dataset – The dataset the model the object belongs to was trained on; e.g. imagenet, cifar10

  • training_scheme – The training scheme used on the model the object belongs to if any; e.g. augmented

  • sparse_name – The name describing the sparsification of the model the object belongs to, e.g. base, pruned, pruned_quant

  • sparse_category – The degree of sparsification of the model the object belongs to; e.g. none, conservative (~100% baseline metric), moderate (>=99% baseline metric), aggressive (<99% baseline metric)

  • sparse_target – The deployment target of sparsification of the model the object belongs to; e.g. edge, deepsparse, deepsparse_throughput, gpu

  • override_folder_name – Override for the name of the folder to save this file under

  • override_parent_path – Path to override the default save path for where to save the parent folder for this file under

  • force_token_refresh – True to refresh the auth token, False otherwise

Returns

The created model

sparsezoo.models.detection.yolo module

YOLO models:

https://arxiv.org/abs/1804.02767

sparsezoo.models.detection.yolo.yolo_v3(sub_architecture: str = 'spp', framework: str = 'pytorch', repo: str = 'ultralytics', dataset: str = 'coco', training_scheme: Optional[str] = None, sparse_name: str = 'base', sparse_category: str = 'none', sparse_target: Optional[str] = None, override_folder_name: Optional[str] = None, override_parent_path: Optional[str] = None, force_token_refresh: bool = False) → sparsezoo.objects.model.Model[source]

Convenience function for getting an yolo_v3 model

Parameters

  • sub_architecture – The sub architecture of the model the object belongs to; e.g. spp

  • framework – The framework the model the object belongs to was trained on; e.g. pytorch, tensorflow

  • repo – the source repo for the model the object belongs to; e.g. sparseml, torchvision

  • dataset – The dataset the model the object belongs to was trained on; e.g. imagenet, cifar10

  • training_scheme – The training scheme used on the model the object belongs to if any; e.g. augmented

  • sparse_name – The name describing the sparsification of the model the object belongs to, e.g. base, pruned, pruned_quant

  • sparse_category – The degree of sparsification of the model the object belongs to; e.g. none, conservative (~100% baseline metric), moderate (>=99% baseline metric), aggressive (<99% baseline metric)

  • sparse_target – The deployment target of sparsification of the model the object belongs to; e.g. edge, deepsparse, deepsparse_throughput, gpu

  • override_folder_name – Override for the name of the folder to save this file under

  • override_parent_path – Path to override the default save path for where to save the parent folder for this file under

  • force_token_refresh – True to refresh the auth token, False otherwise

Returns

The created model

Module contents

Image detection models