sparseml.pytorch.framework package

Submodules

sparseml.pytorch.framework.info module

Functionality related to detecting and getting information for support and sparsification in the PyTorch framework.

sparseml.pytorch.framework.info.detect_framework(item: Any) → sparseml.base.Framework [source]

Detect the supported ML framework for a given item specifically for the pytorch package. Supported input types are the following: - A Framework enum - A string of any case representing the name of the framework

(deepsparse, onnx, keras, pytorch, tensorflow_v1)

A supported file type within the framework such as model files: (onnx, pth, h5, pb)
An object from a supported ML framework such as a model instance

If the framework cannot be determined, will return Framework.unknown

Parameters: item (Any) – The item to detect the ML framework for
Returns: The detected framework from the given item
Return type: Framework

sparseml.pytorch.framework.info.framework_info() → sparseml.framework.info.FrameworkInfo [source]

Detect the information for the onnx/onnxruntime framework such as package versions, availability for core actions such as training and inference, sparsification support, and inference provider support.

Returns: The framework info for onnx/onnxruntime
Return type: FrameworkInfo

sparseml.pytorch.framework.info.is_supported(item: Any) → bool[source]

Parameters: item (Any) – The item to detect the support for
Returns: True if the item is supported by pytorch, False otherwise
Return type: bool

Module contents

Functionality related to integrating with, detecting, and getting information for support and sparsification in the PyTorch framework.