mindarmour.utils

Util methods of MindArmour.

class mindarmour.utils.GradWrap(network)

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

Parameters

network (Cell) – The target network to wrap.

Examples

>>> data = Tensor(np.ones([1, 1, 32, 32]).astype(np.float32)*0.01)
>>> label = Tensor(np.ones([1, 10]).astype(np.float32))
>>> num_classes = 10
>>> sens = np.zeros((data.shape[0], num_classes)).astype(np.float32)
>>> sens[:, 1] = 1.0
>>> net = NET()
>>> wrap_net = GradWrap(net)
>>> wrap_net(data, Tensor(sens))

construct(inputs, weight)

Compute jacobian matrix.

Parameters

• inputs (Tensor) – Inputs of network.

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

Returns

Tensor, Jacobian matrix.

class mindarmour.utils.GradWrapWithLoss(network)

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

Parameters

network (Cell) – The target network to wrap.

Examples

>>> data = Tensor(np.ones([1, 1, 32, 32]).astype(np.float32)*0.01)
>>> label = Tensor(np.ones([1, 10]).astype(np.float32))
>>> net = NET()
>>> loss_fn = nn.SoftmaxCrossEntropyWithLogits()
>>> loss_net = WithLossCell(net, loss_fn)
>>> grad_all = GradWrapWithLoss(loss_net)
>>> out_grad = grad_all(data, labels)

construct(inputs, labels)

Compute gradient of inputs with labels and weight.

Parameters

• inputs (Tensor) – Inputs of network.

• labels (Tensor) – Labels of inputs.

Returns

Tensor, gradient matrix.

class mindarmour.utils.LogUtil

Logging module.

Raises

SyntaxError – If create this class.

add_handler(handler)

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)

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

Parameters

• tag (str) – Logger tag.

• msg (str) – Logger message.

• args (Any) – Auxiliary value.

error(tag, msg, *args)

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

Parameters

• tag (str) – Logger tag.

• msg (str) – Logger message.

• args (Any) – Auxiliary value.

static get_instance()

Get instance of class LogUtil.

Returns

Object, instance of class LogUtil.

info(tag, msg, *args)

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

Parameters

• tag (str) – Logger tag.

• msg (str) – Logger message.

• args (Any) – Auxiliary value.

set_level(level)

Set the logging level of this logger, level must be an integer or a string.

Parameters

level (Union[int, str]) – Level of logger.

warn(tag, msg, *args)

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

Parameters

• tag (str) – Logger tag.

• msg (str) – Logger message.

• args (Any) – Auxiliary value.