def attribute(
self,
inputs: Union[Tensor, Tuple[Tensor, ...]],
baselines: Union[Tensor, Tuple[Tensor, ...],
Callable[..., Union[Tensor, Tuple[Tensor, ...]]]],
target: TargetType = None,
additional_forward_args: Any = None,
return_convergence_delta: bool = False,
attribute_to_layer_input: bool = False,
custom_attribution_func: Union[None, Callable[..., Tuple[Tensor,
...]]] = None,
) -> Union[Tensor, Tuple[Tensor, ...], Tuple[Union[Tensor, Tuple[
Tensor, ...]], Tensor]]:
r"""
Args:
inputs (tensor or tuple of tensors): Input for which layer
attributions are computed. If forward_func takes a single
tensor as input, a single input tensor should be provided.
If forward_func takes multiple tensors as input, a tuple
of the input tensors should be provided. It is assumed
that for all given input tensors, dimension 0 corresponds
to the number of examples (aka batch size), and if
multiple input tensors are provided, the examples must
be aligned appropriately.
baselines (tensor, tuple of tensors, callable):
Baselines define reference samples that are compared with
the inputs. In order to assign attribution scores DeepLift
computes the differences between the inputs/outputs and
corresponding references. Baselines can be provided as:
- a single tensor, if inputs is a single tensor, with
the first dimension equal to the number of examples
in the baselines' distribution. The remaining dimensions
must match with input tensor's dimension starting from
the second dimension.
- a tuple of tensors, if inputs is a tuple of tensors,
with the first dimension of any tensor inside the tuple
equal to the number of examples in the baseline's
distribution. The remaining dimensions must match
the dimensions of the corresponding input tensor
starting from the second dimension.
- callable function, optionally takes `inputs` as an
argument and either returns a single tensor
or a tuple of those.
It is recommended that the number of samples in the baselines'
tensors is larger than one.
target (int, tuple, tensor or list, optional): Output indices for
which gradients are computed (for classification cases,
this is usually the target class).
If the network returns a scalar value per example,
no target index is necessary.
For general 2D outputs, targets can be either:
- a single integer or a tensor containing a single
integer, which is applied to all input examples
- a list of integers or a 1D tensor, with length matching
the number of examples in inputs (dim 0). Each integer
is applied as the target for the corresponding example.
For outputs with > 2 dimensions, targets can be either:
- A single tuple, which contains #output_dims - 1
elements. This target index is applied to all examples.
- A list of tuples with length equal to the number of
examples in inputs (dim 0), and each tuple containing
#output_dims - 1 elements. Each tuple is applied as the
target for the corresponding example.
Default: None
additional_forward_args (any, optional): If the forward function
requires additional arguments other than the inputs for
which attributions should not be computed, this argument
can be provided. It must be either a single additional
argument of a Tensor or arbitrary (non-tuple) type or a tuple
containing multiple additional arguments including tensors
or any arbitrary python types. These arguments are provided to
forward_func in order, following the arguments in inputs.
Note that attributions are not computed with respect
to these arguments.
Default: None
return_convergence_delta (bool, optional): Indicates whether to return
convergence delta or not. If `return_convergence_delta`
is set to True convergence delta will be returned in
a tuple following attributions.
Default: False
attribute_to_layer_input (bool, optional): Indicates whether to
compute the attributions with respect to the layer input
or output. If `attribute_to_layer_input` is set to True
then the attributions will be computed with respect to
layer inputs, otherwise it will be computed with respect
to layer outputs.
Note that currently it assumes that both the inputs and
outputs of internal layers are single tensors.
Support for multiple tensors will be added later.
Default: False
custom_attribution_func (callable, optional): A custom function for
computing final attribution scores. This function can take
at least one and at most three arguments with the
following signature:
- custom_attribution_func(multipliers)
- custom_attribution_func(multipliers, inputs)
- custom_attribution_func(multipliers, inputs, baselines)
In case this function is not provided, we use the default
logic defined as: multipliers * (inputs - baselines)
It is assumed that all input arguments, `multipliers`,
`inputs` and `baselines` are provided in tuples of same
length. `custom_attribution_func` returns a tuple of
attribution tensors that have the same length as the
`inputs`.
Default: None
Returns:
**attributions** or 2-element tuple of **attributions**, **delta**:
- **attributions** (*tensor* or tuple of *tensors*):
Attribution score computed based on DeepLift's rescale rule
with respect to layer's inputs or outputs. Attributions
will always be the same size as the provided layer's inputs
or outputs, depending on whether we attribute to the inputs
or outputs of the layer.
Attributions are returned in a tuple based on whether
the layer inputs / outputs are contained in a tuple
from a forward hook. For standard modules, inputs of
a single tensor are usually wrapped in a tuple, while
outputs of a single tensor are not.
- **delta** (*tensor*, returned if return_convergence_delta=True):
This is computed using the property that the
total sum of forward_func(inputs) - forward_func(baselines)
must be very close to the total sum of attributions
computed based on approximated SHAP values using
DeepLift's rescale rule.
Delta is calculated for each example input and baseline pair,
meaning that the number of elements in returned delta tensor
is equal to the
`number of examples in input` * `number of examples
in baseline`. The deltas are ordered in the first place by
input example, followed by the baseline.
Note that the logic described for deltas is guaranteed
when the default logic for attribution computations is used,
meaning that the `custom_attribution_func=None`, otherwise
it is not guaranteed and depends on the specifics of the
`custom_attribution_func`.
Examples::
>>> # ImageClassifier takes a single input tensor of images Nx3x32x32,
>>> # and returns an Nx10 tensor of class probabilities.
>>> net = ImageClassifier()
>>> # creates an instance of LayerDeepLift to interpret target
>>> # class 1 with respect to conv4 layer.
>>> dl = LayerDeepLiftShap(net, net.conv4)
>>> input = torch.randn(2, 3, 32, 32, requires_grad=True)
>>> # Computes shap values using deeplift for class 3.
>>> attribution = dl.attribute(input, target=3)
"""
inputs = _format_input(inputs)
baselines = _format_callable_baseline(baselines, inputs)
assert isinstance(
baselines[0], torch.Tensor
) and baselines[0].shape[0] > 1, (
"Baselines distribution has to be provided in form of a torch.Tensor"
" with more than one example but found: {}."
" If baselines are provided in shape of scalars or with a single"
" baseline example, `LayerDeepLift`"
" approach can be used instead.".format(baselines[0]))
# batch sizes
inp_bsz = inputs[0].shape[0]
base_bsz = baselines[0].shape[0]
(
exp_inp,
exp_base,
exp_target,
exp_addit_args,
) = DeepLiftShap._expand_inputs_baselines_targets(
self, baselines, inputs, target, additional_forward_args)
attributions = LayerDeepLift.attribute.__wrapped__( # type: ignore
self,
exp_inp,
exp_base,
target=exp_target,
additional_forward_args=exp_addit_args,
return_convergence_delta=cast(Literal[True, False],
return_convergence_delta),
attribute_to_layer_input=attribute_to_layer_input,
custom_attribution_func=custom_attribution_func,
)
if return_convergence_delta:
attributions, delta = attributions
if isinstance(attributions, tuple):
attributions = tuple(
DeepLiftShap._compute_mean_across_baselines(
self, inp_bsz, base_bsz, cast(Tensor, attrib))
for attrib in attributions)
else:
attributions = DeepLiftShap._compute_mean_across_baselines(
self, inp_bsz, base_bsz, attributions)
if return_convergence_delta:
return attributions, delta
else:
return attributions
def attribute(
self,
inputs: TensorOrTupleOfTensorsGeneric,
baselines: Union[TensorOrTupleOfTensorsGeneric,
Callable[..., TensorOrTupleOfTensorsGeneric]],
n_samples: int = 5,
stdevs: Union[float, Tuple[float, ...]] = 0.0,
target: TargetType = None,
additional_forward_args: Any = None,
return_convergence_delta: bool = False,
) -> Union[TensorOrTupleOfTensorsGeneric, Tuple[
TensorOrTupleOfTensorsGeneric, Tensor]]:
r"""
Args:
inputs (tensor or tuple of tensors): Input for which SHAP attribution
values are computed. If `forward_func` takes a single
tensor as input, a single input tensor should be provided.
If `forward_func` takes multiple tensors as input, a tuple
of the input tensors should be provided. It is assumed
that for all given input tensors, dimension 0 corresponds
to the number of examples, and if multiple input tensors
are provided, the examples must be aligned appropriately.
baselines (tensor, tuple of tensors, callable):
Baselines define the starting point from which expectation
is computed and can be provided as:
- a single tensor, if inputs is a single tensor, with
the first dimension equal to the number of examples
in the baselines' distribution. The remaining dimensions
must match with input tensor's dimension starting from
the second dimension.
- a tuple of tensors, if inputs is a tuple of tensors,
with the first dimension of any tensor inside the tuple
equal to the number of examples in the baseline's
distribution. The remaining dimensions must match
the dimensions of the corresponding input tensor
starting from the second dimension.
- callable function, optionally takes `inputs` as an
argument and either returns a single tensor
or a tuple of those.
It is recommended that the number of samples in the baselines'
tensors is larger than one.
n_samples (int, optional): The number of randomly generated examples
per sample in the input batch. Random examples are
generated by adding gaussian random noise to each sample.
Default: `5` if `n_samples` is not provided.
stdevs (float, or a tuple of floats optional): The standard deviation
of gaussian noise with zero mean that is added to each
input in the batch. If `stdevs` is a single float value
then that same value is used for all inputs. If it is
a tuple, then it must have the same length as the inputs
tuple. In this case, each stdev value in the stdevs tuple
corresponds to the input with the same index in the inputs
tuple.
Default: 0.0
target (int, tuple, tensor or list, optional): Output indices for
which gradients are computed (for classification cases,
this is usually the target class).
If the network returns a scalar value per example,
no target index is necessary.
For general 2D outputs, targets can be either:
- a single integer or a tensor containing a single
integer, which is applied to all input examples
- a list of integers or a 1D tensor, with length matching
the number of examples in inputs (dim 0). Each integer
is applied as the target for the corresponding example.
For outputs with > 2 dimensions, targets can be either:
- A single tuple, which contains #output_dims - 1
elements. This target index is applied to all examples.
- A list of tuples with length equal to the number of
examples in inputs (dim 0), and each tuple containing
#output_dims - 1 elements. Each tuple is applied as the
target for the corresponding example.
Default: None
additional_forward_args (any, optional): If the forward function
requires additional arguments other than the inputs for
which attributions should not be computed, this argument
can be provided. It can contain a tuple of ND tensors or
any arbitrary python type of any shape.
In case of the ND tensor the first dimension of the
tensor must correspond to the batch size. It will be
repeated for each `n_steps` for each randomly generated
input sample.
Note that the gradients are not computed with respect
to these arguments.
Default: None
return_convergence_delta (bool, optional): Indicates whether to return
convergence delta or not. If `return_convergence_delta`
is set to True convergence delta will be returned in
a tuple following attributions.
Default: False
Returns:
**attributions** or 2-element tuple of **attributions**, **delta**:
- **attributions** (*tensor* or tuple of *tensors*):
Attribution score computed based on GradientSHAP with respect
to each input feature. Attributions will always be
the same size as the provided inputs, with each value
providing the attribution of the corresponding input index.
If a single tensor is provided as inputs, a single tensor is
returned. If a tuple is provided for inputs, a tuple of
corresponding sized tensors is returned.
- **delta** (*tensor*, returned if return_convergence_delta=True):
This is computed using the property that the total
sum of forward_func(inputs) - forward_func(baselines)
must be very close to the total sum of the attributions
based on GradientSHAP.
Delta is calculated for each example in the input after adding
`n_samples` times gaussian noise to each of them. Therefore,
the dimensionality of the deltas tensor is equal to the
`number of examples in the input` * `n_samples`
The deltas are ordered by each input example and `n_samples`
noisy samples generated for it.
Examples::
>>> # ImageClassifier takes a single input tensor of images Nx3x32x32,
>>> # and returns an Nx10 tensor of class probabilities.
>>> net = ImageClassifier()
>>> gradient_shap = GradientShap(net)
>>> input = torch.randn(3, 3, 32, 32, requires_grad=True)
>>> # choosing baselines randomly
>>> baselines = torch.randn(20, 3, 32, 32)
>>> # Computes gradient shap for the input
>>> # Attribution size matches input size: 3x3x32x32
>>> attribution = gradient_shap.attribute(input, baselines,
target=5)
"""
# since `baselines` is a distribution, we can generate it using a function
# rather than passing it as an input argument
baselines = _format_callable_baseline(baselines, inputs)
assert isinstance(baselines[0], torch.Tensor), (
"Baselines distribution has to be provided in a form "
"of a torch.Tensor {}.".format(baselines[0]))
input_min_baseline_x_grad = InputBaselineXGradient(
self.forward_func, self.multiplies_by_inputs)
input_min_baseline_x_grad.gradient_func = self.gradient_func
nt = NoiseTunnel(input_min_baseline_x_grad)
# NOTE: using attribute.__wrapped__ to not log
attributions = nt.attribute.__wrapped__(
nt, # self
inputs,
nt_type="smoothgrad",
nt_samples=n_samples,
stdevs=stdevs,
draw_baseline_from_distrib=True,
baselines=baselines,
target=target,
additional_forward_args=additional_forward_args,
return_convergence_delta=return_convergence_delta,
)
return attributions
