mindarmour.utils

Util methods of MindArmour.

• class mindarmour.utils.LogUtil[source]

• Logging module.

  • Raises

  • SyntaxError – If create this class.

  • addhandler(_handler)[source]

  • Add other handler supported by logging module.

    • Parameters

    • handler (logging.Handler) – Other handler supported by logging module.

    • Raises

    • ValueError – If handler is not an instance of logging.Handler.

  • debug(tag, msg, *args)[source]

  • Log ‘[tag] msg % args’ with severity ‘DEBUG’.

    • Parameters

    • • tag (str) – Logger tag.

      • msg (str) – Logger message.

      • args (Any) – Auxiliary value.

  • error(tag, msg, *args)[source]

  • Log ‘[tag] msg % args’ with severity ‘ERROR’.

    • Parameters

    • • tag (str) – Logger tag.

      • msg (str) – Logger message.

      • args (Any) – Auxiliary value.

  • static get_instance()[source]

  • Get instance of class LogUtil.

    • Returns
    • Object, instance of class LogUtil.

  • info(tag, msg, *args)[source]

  • Log ‘[tag] msg % args’ with severity ‘INFO’.

    • Parameters

    • • tag (str) – Logger tag.

      • msg (str) – Logger message.

      • args (Any) – Auxiliary value.

  • setlevel(_level)[source]

  • Set the logging level of this logger, level must be an integer or astring.

    • Parameters
    • level (Union__[int, str]) – Level of logger.

  • warn(tag, msg, *args)[source]

  • Log ‘[tag] msg % args’ with severity ‘WARNING’.

    • Parameters

    • • tag (str) – Logger tag.

      • msg (str) – Logger message.

      • args (Any) – Auxiliary value.

• class mindarmour.utils.GradWrapWithLoss(network)[source]

• Construct a network to compute the gradient of loss function in input spaceand weighted by weight.

  • construct(inputs, labels, weight)[source]

  • Compute gradient of inputs with labels and weight.

    • Parameters

    • • inputs (Tensor) – Inputs of network.

      • labels (Tensor) – Labels of inputs.

      • weight (Tensor) – Weight of each gradient, weight has the sameshape with labels.

    • Returns

    • Tensor, gradient matrix.

• class mindarmour.utils.GradWrap(network)[source]

• Construct a network to compute the gradient of network outputs in inputspace and weighted by weight, expressed as a jacobian matrix.

  • construct(inputs, weight)[source]

  • Compute jacobian matrix.

    • Parameters

    • • inputs (Tensor) – Inputs of network.

      • weight (Tensor) – Weight of each gradient, weight has the sameshape with labels.

    • Returns

    • Tensor, Jacobian matrix.