sparsezoo.models.classification package

Submodules

sparsezoo.models.classification.efficientnet module

EfficientNet models:

https://arxiv.org/abs/1905.11946

sparsezoo.models.classification.efficientnet.efficientnet_b0(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 efficientnet b0 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.classification.efficientnet.efficientnet_b4(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 efficientnet b0 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.classification.inception module

Inception models:

https://arxiv.org/abs/1512.00567

sparsezoo.models.classification.inception.inception_v3(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 inception_v3 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.classification.mobilenet module

MobileNet models:

https://arxiv.org/abs/1704.04861 https://arxiv.org/abs/1801.04381

sparsezoo.models.classification.mobilenet.mobilenet_v1(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a mobilenet_v1 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.classification.mobilenet.mobilenet_v2(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a mobilenet_v2 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.classification.resnet module

ResNet models:

https://arxiv.org/abs/1512.03385

sparsezoo.models.classification.resnet.resnet_101(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a resnet 101 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.classification.resnet.resnet_101_2x(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a resnet 101 2x width 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.classification.resnet.resnet_152(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a resnet 152 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.classification.resnet.resnet_18(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a resnet 18 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.classification.resnet.resnet_34(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a resnet 34 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.classification.resnet.resnet_50(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a resnet 50 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.classification.resnet.resnet_50_2x(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a resnet 50 2x width 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.classification.vgg module

VGG models:

https://arxiv.org/abs/1409.1556

sparsezoo.models.classification.vgg.vgg_11(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a vgg 11 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.classification.vgg.vgg_11bn(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a batch normalized vgg 11 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.classification.vgg.vgg_13(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a vgg 13 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.classification.vgg.vgg_13bn(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a batch normalized vgg 13 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.classification.vgg.vgg_16(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a vgg 16 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.classification.vgg.vgg_16bn(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a batch normalized vgg 16 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.classification.vgg.vgg_19(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a vgg 19 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.classification.vgg.vgg_19bn(framework: str = 'pytorch', repo: str = 'sparseml', dataset: str = 'imagenet', 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 a batch normalized vgg 19 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

Module contents

Image classification models