def _lime_test_assert(
self,
model: Callable,
test_input: TensorOrTupleOfTensorsGeneric,
expected_attr,
expected_coefs_only=None,
feature_mask: Union[None, TensorOrTupleOfTensorsGeneric] = None,
additional_input: Any = None,
perturbations_per_eval: Tuple[int, ...] = (1, ),
baselines: BaselineType = None,
target: Union[None, int] = 0,
n_perturb_samples: int = 100,
alpha: float = 1.0,
delta: float = 1.0,
batch_attr: bool = False,
) -> None:
for batch_size in perturbations_per_eval:
lime = Lime(
model,
similarity_func=get_exp_kernel_similarity_function(
"cosine", 10.0),
)
attributions = lime.attribute(
test_input,
target=target,
feature_mask=feature_mask,
additional_forward_args=additional_input,
baselines=baselines,
perturbations_per_eval=batch_size,
n_perturb_samples=n_perturb_samples,
alpha=alpha,
)
assertTensorTuplesAlmostEqual(self,
attributions,
expected_attr,
delta=delta,
mode="max")
if expected_coefs_only is not None:
# Test with return_input_shape = False
attributions = lime.attribute(
test_input,
target=target,
feature_mask=feature_mask,
additional_forward_args=additional_input,
baselines=baselines,
perturbations_per_eval=batch_size,
n_perturb_samples=n_perturb_samples,
alpha=alpha,
return_input_shape=False,
)
assertTensorAlmostEqual(self,
attributions,
expected_coefs_only,
delta=delta,
mode="max")
lime_alt = LimeBase(
model,
lasso_interpretable_model_trainer,
get_exp_kernel_similarity_function("euclidean", 1000.0),
alt_perturb_func,
False,
None,
alt_to_interp_rep,
)
# Test with equivalent sampling in original input space
formatted_inputs, baselines = _format_input_baseline(
test_input, baselines)
if feature_mask is None:
(
formatted_feature_mask,
num_interp_features,
) = _construct_default_feature_mask(formatted_inputs)
else:
formatted_feature_mask = _format_input(feature_mask)
num_interp_features = int(
max(
torch.max(single_inp).item()
for single_inp in feature_mask) + 1)
if batch_attr:
attributions = lime_alt.attribute(
test_input,
target=target,
feature_mask=formatted_feature_mask if isinstance(
test_input, tuple) else formatted_feature_mask[0],
additional_forward_args=additional_input,
baselines=baselines,
perturbations_per_eval=batch_size,
n_perturb_samples=n_perturb_samples,
alpha=alpha,
num_interp_features=num_interp_features,
)
assertTensorAlmostEqual(self,
attributions,
expected_coefs_only,
delta=delta,
mode="max")
return
bsz = formatted_inputs[0].shape[0]
for (
curr_inps,
curr_target,
curr_additional_args,
curr_baselines,
curr_feature_mask,
expected_coef_single,
) in _batch_example_iterator(
bsz,
test_input,
target,
additional_input,
baselines
if isinstance(test_input, tuple) else baselines[0],
formatted_feature_mask if isinstance(
test_input, tuple) else formatted_feature_mask[0],
expected_coefs_only,
):
attributions = lime_alt.attribute(
curr_inps,
target=curr_target,
feature_mask=curr_feature_mask,
additional_forward_args=curr_additional_args,
baselines=curr_baselines,
perturbations_per_eval=batch_size,
n_perturb_samples=n_perturb_samples,
alpha=alpha,
num_interp_features=num_interp_features,
)
assertTensorAlmostEqual(
self,
attributions,
expected_coef_single,
delta=delta,
mode="max",
)
def attribute(
self,
inputs: Union[Tensor, Tuple[Tensor, ...]],
baselines: BaselineType = None,
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 (scalar, tensor, tuple of scalars or tensors, optional):
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
exactly the same dimensions as inputs or the first
dimension is one and the remaining dimensions match
with inputs.
- a single scalar, if inputs is a single tensor, which will
be broadcasted for each input value in input tensor.
- a tuple of tensors or scalars, the baseline corresponding
to each tensor in the inputs' tuple can be:
- either a tensor with matching dimensions to
corresponding tensor in the inputs' tuple
or the first dimension is one and the remaining
dimensions match with the corresponding
input tensor.
- or a scalar, corresponding to a tensor in the
inputs' tuple. This scalar value is broadcasted
for corresponding input tensor.
In the cases when `baselines` is not provided, we internally
use zero scalar corresponding to each input tensor.
Default: None
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 attribution 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 input, otherwise it will be computed with respect
to layer output.
Note that currently it is assumed that either the input
or the output of internal layer, depending on whether we
attribute to the input or output, is a single tensor.
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.
If the layer input / output is a single tensor, then
just a tensor is returned; if the layer input / output
has multiple tensors, then a corresponding tuple
of 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 equal the
total sum of the attributions computed based on DeepLift's
rescale rule.
Delta is calculated per example, meaning that the number of
elements in returned delta tensor is equal to the number of
of examples in input.
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 = LayerDeepLift(net, net.conv4)
>>> input = torch.randn(1, 3, 32, 32, requires_grad=True)
>>> # Computes deeplift attribution scores for conv4 layer and class 3.
>>> attribution = dl.attribute(input, target=1)
"""
inputs = _format_input(inputs)
baselines = _format_baseline(baselines, inputs)
gradient_mask = apply_gradient_requirements(inputs)
_validate_input(inputs, baselines)
baselines = _tensorize_baseline(inputs, baselines)
main_model_pre_hook = self._pre_hook_main_model()
self.model.apply(self._register_hooks)
additional_forward_args = _format_additional_forward_args(
additional_forward_args)
input_base_additional_args = _expand_additional_forward_args(
additional_forward_args, 2, ExpansionTypes.repeat)
expanded_target = _expand_target(target,
2,
expansion_type=ExpansionTypes.repeat)
wrapped_forward_func = self._construct_forward_func(
self.model,
(inputs, baselines),
expanded_target,
input_base_additional_args,
)
def chunk_output_fn(out: TensorOrTupleOfTensorsGeneric, ) -> Sequence:
if isinstance(out, Tensor):
return out.chunk(2)
return tuple(out_sub.chunk(2) for out_sub in out)
(gradients, attrs, is_layer_tuple) = compute_layer_gradients_and_eval(
wrapped_forward_func,
self.layer,
inputs,
attribute_to_layer_input=attribute_to_layer_input,
output_fn=lambda out: chunk_output_fn(out),
)
attr_inputs = tuple(map(lambda attr: attr[0], attrs))
attr_baselines = tuple(map(lambda attr: attr[1], attrs))
gradients = tuple(map(lambda grad: grad[0], gradients))
if custom_attribution_func is None:
attributions = tuple((input - baseline) * gradient
for input, baseline, gradient in zip(
attr_inputs, attr_baselines, gradients))
else:
attributions = _call_custom_attribution_func(
custom_attribution_func, gradients, attr_inputs,
attr_baselines)
# remove hooks from all activations
main_model_pre_hook.remove()
self._remove_hooks()
undo_gradient_requirements(inputs, gradient_mask)
return _compute_conv_delta_and_format_attrs(
self,
return_convergence_delta,
attributions,
baselines,
inputs,
additional_forward_args,
target,
is_layer_tuple,
)
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(
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: Union[Tensor, Tuple[Tensor, ...]],
target: TargetType = None,
additional_forward_args: Any = None,
attribute_to_layer_input: bool = False,
relu_attributions: bool = False,
) -> Union[Tensor, Tuple[Tensor, ...]]:
r"""
Args:
inputs (tensor or tuple of tensors): Input for which 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, and if multiple input tensors
are provided, the examples must be aligned appropriately.
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
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 the
layer input, otherwise it will be computed with respect
to layer output.
Note that currently it is assumed that either the input
or the outputs of internal layers, depending on whether we
attribute to the input or output, are single tensors.
Support for multiple tensors will be added later.
Default: False
relu_attributions (bool, optional): Indicates whether to
apply a ReLU operation on the final attribution,
returning only non-negative attributions. Setting this
flag to True matches the original GradCAM algorithm,
otherwise, by default, both positive and negative
attributions are returned.
Default: False
Returns:
*tensor* or tuple of *tensors* of **attributions**:
- **attributions** (*tensor* or tuple of *tensors*):
Attributions based on GradCAM method.
Attributions will be the same size as the
output of the given layer, except for dimension 2,
which will be 1 due to summing over channels.
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.
Examples::
# >>> # ImageClassifier takes a single input tensor of images Nx3x32x32,
# >>> # and returns an Nx10 tensor of class probabilities.
# >>> # It contains a layer conv4, which is an instance of nn.conv2d,
# >>> # and the output of this layer has dimensions Nx50x8x8.
# >>> # It is the last convolution layer, which is the recommended
# >>> # use case for GradCAM.
# >>> net = ImageClassifier()
# >>> layer_gc = LayerGradCam(net, net.conv4)
# >>> input = torch.randn(2, 3, 32, 32, requires_grad=True)
# >>> # Computes layer GradCAM for class 3.
# >>> # attribution size matches layer output except for dimension
# >>> # 1, so dimensions of attr would be Nx1x8x8.
# >>> attr = layer_gc.attribute(input, 3)
# >>> # GradCAM attributions are often upsampled and viewed as a
# >>> # mask to the input, since the convolutional layer output
# >>> # spatially matches the original input image.
# >>> # This can be done with LayerAttribution's interpolate method.
# >>> upsampled_attr = LayerAttribution.interpolate(attr, (32, 32))
"""
inputs = _format_input(inputs)
additional_forward_args = _format_additional_forward_args(
additional_forward_args)
gradient_mask = apply_gradient_requirements(inputs)
# Returns gradient of output with respect to
# hidden layer and hidden layer evaluated at each input.
layer_gradients, layer_evals, is_layer_tuple = compute_layer_gradients_and_eval(
self.forward_func,
self.layer,
inputs,
target,
additional_forward_args,
device_ids=self.device_ids,
attribute_to_layer_input=attribute_to_layer_input,
)
undo_gradient_requirements(inputs, gradient_mask)
# Gradient Calculation end
# what I add: shape from PyG to General PyTorch
layer_gradients = tuple(
layer_grad.transpose(0, 1).unsqueeze(0)
for layer_grad in layer_gradients)
layer_evals = tuple(
layer_eval.transpose(0, 1).unsqueeze(0)
for layer_eval in layer_evals)
# end
summed_grads = tuple(
torch.mean(
layer_grad,
dim=tuple(x for x in range(2, len(layer_grad.shape))),
keepdim=True,
) for layer_grad in layer_gradients)
scaled_acts = tuple(
torch.sum(summed_grad * layer_eval, dim=1, keepdim=True)
for summed_grad, layer_eval in zip(summed_grads, layer_evals))
if relu_attributions:
scaled_acts = tuple(
F.relu(scaled_act) for scaled_act in scaled_acts)
# what I add: shape from General PyTorch to PyG
scaled_acts = tuple(
scaled_act.squeeze(0).transpose(0, 1)
for scaled_act in scaled_acts)
# end
return _format_attributions(is_layer_tuple, scaled_acts)
