sy00000
/
mindspore
forked from OSSInnovation/mindspore
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

modify examples of explainer.benchmark

This commit is contained in:
lixiaohui 2021-03-29 10:50:29 +08:00
parent 62fbbf9eb7
commit a8975af9b8
11 changed files with 39 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
mindspore/explainer/_image_classification_runner.py
View File

@ -89,6 +89,7 @@ class ImageClassificationRunner:
>>> # Load the checkpoint
>>> param_dict = load_checkpoint("/path/to/checkpoint")
>>> load_param_into_net(net, param_dict)
[]
>>>
>>> # Prepare the dataset for explaining and evaluation.
>>> # The detail of create_dataset_cifar10 method is shown in model_zoo.official.cv.alexnet.src.dataset.py
@ -105,8 +106,6 @@ class ImageClassificationRunner:
>>>
>>> runner = ImageClassificationRunner("./summary_dir", (dataset, labels), net, activation_fn)
>>> runner.register_saliency(explainers=explainers, benchmarkers=benchmarkers)
>>> runner.register_uncertainty()
>>> runner.register_hierarchical_occlusion()
>>> runner.run()
"""

3
mindspore/explainer/benchmark/_attribution/class_sensitivity.py
View File

@ -57,7 +57,8 @@ class ClassSensitivity(LabelAgnosticMetric):
>>> input_x = ms.Tensor(np.random.rand(1, 3, 32, 32), ms.float32)
>>> class_sensitivity = ClassSensitivity()
>>> res = class_sensitivity.evaluate(gradient, input_x)
>>> print(res)
>>> print(res.shape)
(1,)
"""
self._check_evaluate_param(explainer, inputs)

22
mindspore/explainer/benchmark/_attribution/faithfulness.py
View File

@ -365,15 +365,6 @@ class Faithfulness(LabelSensitiveMetric):
metric (str, optional): The specifi metric to quantify faithfulness.
Options: "DeletionAUC", "InsertionAUC", "NaiveFaithfulness".
Default: 'NaiveFaithfulness'.
Examples:
>>> from mindspore import nn
>>> from mindspore.explainer.benchmark import Faithfulness
>>> # init a `Faithfulness` object
>>> num_labels = 10
>>> metric = "InsertionAUC"
>>> activation_fn = nn.Softmax()
>>> faithfulness = Faithfulness(num_labels, activation_fn, metric)
"""
_methods = [NaiveFaithfulness, DeletionAUC, InsertionAUC]
@ -418,9 +409,15 @@ class Faithfulness(LabelSensitiveMetric):
Examples:
>>> import numpy as np
>>> import mindspore as ms
>>> from mindspore import nn
>>> from mindspore.explainer.benchmark import Faithfulness
>>> from mindspore.explainer.explanation import Gradient
>>>
>>>
>>> # init a `Faithfulness` object
>>> num_labels = 10
>>> metric = "InsertionAUC"
>>> activation_fn = nn.Softmax()
>>> faithfulness = Faithfulness(num_labels, activation_fn, metric)
>>> # The detail of LeNet5 is shown in model_zoo.official.cv.lenet.src.lenet.py
>>> net = LeNet5(10, num_channel=3)
>>> gradient = Gradient(net)
@ -429,10 +426,13 @@ class Faithfulness(LabelSensitiveMetric):
>>> # usage 1: input the explainer and the data to be explained,
>>> # faithfulness is a Faithfulness instance
>>> res = faithfulness.evaluate(gradient, inputs, targets)
>>> print(res.shape)
(1,)
>>> # usage 2: input the generated saliency map
>>> saliency = gradient(inputs, targets)
>>> res = faithfulness.evaluate(gradient, inputs, targets, saliency)
>>> print(res)
>>> print(res.shape)
(1,)
"""
self._check_evaluate_param(explainer, inputs, targets, saliency)

18
mindspore/explainer/benchmark/_attribution/localization.py
View File

@ -56,13 +56,7 @@ class Localization(LabelSensitiveMetric):
Args:
num_labels (int): Number of classes in the dataset.
metric (str, optional): Specific metric to calculate localization capability.
Options: "PointingGame", "IoSR".
Default: "PointingGame".
Examples:
>>> from mindspore.explainer.benchmark import Localization
>>> num_labels = 10
>>> localization = Localization(num_labels, "PointingGame")
Options: "PointingGame", "IoSR". Default: "PointingGame".
"""
def __init__(self,
@ -113,6 +107,10 @@ class Localization(LabelSensitiveMetric):
>>> import numpy as np
>>> import mindspore as ms
>>> from mindspore.explainer.explanation import Gradient
>>> from mindspore.explainer.benchmark import Localization
>>>
>>> num_labels = 10
>>> localization = Localization(num_labels, "PointingGame")
>>>
>>> # The detail of LeNet5 is shown in model_zoo.official.cv.lenet.src.lenet.py
>>> net = LeNet5(10, num_channel=3)
@ -124,11 +122,13 @@ class Localization(LabelSensitiveMetric):
>>> # usage 1: input the explainer and the data to be explained,
>>> # localization is a Localization instance
>>> res = localization.evaluate(gradient, inputs, targets, mask=masks)
>>> print(res)
>>> print(res.shape)
(1,)
>>> # usage 2: input the generated saliency map
>>> saliency = gradient(inputs, targets)
>>> res = localization.evaluate(gradient, inputs, targets, saliency, mask=masks)
>>> print(res)
>>> print(res.shape)
(1,)
"""
self._check_evaluate_param_with_mask(explainer, inputs, targets, saliency, mask)

19
mindspore/explainer/benchmark/_attribution/robustness.py
View File

@ -35,15 +35,6 @@ class Robustness(LabelSensitiveMetric):
single label classification tasks, `nn.Softmax` is usually applied. As for multi-label classification tasks,
`nn.Sigmoid` is usually be applied. Users can also pass their own customized `activation_fn` as long as
when combining this function with network, the final output is the probability of the input.
Examples:
>>> from mindspore import nn
>>> from mindspore.explainer.benchmark import Robustness
>>> # Initialize a Robustness benchmarker passing num_labels of the dataset.
>>> num_labels = 10
>>> activation_fn = nn.Softmax()
>>> robustness = Robustness(num_labels, activation_fn)
"""
def __init__(self, num_labels, activation_fn):
@ -79,7 +70,14 @@ class Robustness(LabelSensitiveMetric):
Examples:
>>> import numpy as np
>>> import mindspore as ms
>>> from mindspore import nn
>>> from mindspore.explainer.explanation import Gradient
>>> from mindspore.explainer.benchmark import Robustness
>>>
>>> # Initialize a Robustness benchmarker passing num_labels of the dataset.
>>> num_labels = 10
>>> activation_fn = nn.Softmax()
>>> robustness = Robustness(num_labels, activation_fn)
>>>
>>> # The detail of LeNet5 is shown in model_zoo.official.cv.lenet.src.lenet.py
>>> net = LeNet5(10, num_channel=3)
@ -89,7 +87,8 @@ class Robustness(LabelSensitiveMetric):
>>> target_label = ms.Tensor([0], ms.int32)
>>> # robustness is a Robustness instance
>>> res = robustness.evaluate(gradient, input_x, target_label)
>>> print(res)
>>> print(res.shape)
(1,)
"""
self._check_evaluate_param(explainer, inputs, targets, saliency)

1
mindspore/explainer/explanation/_attribution/_backprop/gradcam.py
View File

@ -87,6 +87,7 @@ class GradCAM(IntermediateLayerAttribution):
>>> label = 5
>>> saliency = gradcam(inputs, label)
>>> print(saliency.shape)
(1, 1, 32, 32)
"""
def __init__(self, network, layer=""):

1
mindspore/explainer/explanation/_attribution/_backprop/gradient.py
View File

@ -62,6 +62,7 @@ class Gradient(Attribution):
>>> label = 5
>>> saliency = gradient(inputs, label)
>>> print(saliency.shape)
(1, 1, 32, 32)
"""
def __init__(self, network):

9
mindspore/explainer/explanation/_attribution/_backprop/modified_relu.py
View File

@ -45,13 +45,6 @@ class ModifiedReLU(Gradient):
Returns:
Tensor, a 4D tensor of shape :math:`(N, 1, H, W)`.
Examples:
>>> inputs = ms.Tensor(np.random.rand(1, 3, 224, 224), ms.float32)
>>> label = 5
>>> # explainer is a "Deconvolution" or "GuidedBackprop" object, parse data and the target label to be
>>> # explained and get the attribution
>>> saliency = explainer(inputs, label)
"""
self._verify_data(inputs, targets)
@ -117,6 +110,7 @@ class Deconvolution(ModifiedReLU):
>>> label = 5
>>> saliency = deconvolution(inputs, label)
>>> print(saliency.shape)
(1, 1, 32, 32)
"""
def __init__(self, network):
@ -161,6 +155,7 @@ class GuidedBackprop(ModifiedReLU):
>>> label = 5
>>> saliency = gbp(inputs, label)
>>> print(saliency.shape)
(1, 1, 32, 32)
"""
def __init__(self, network):

1
mindspore/explainer/explanation/_attribution/_perturbation/occlusion.py
View File

@ -80,6 +80,7 @@ class Occlusion(PerturbationAttribution):
>>> label = ms.Tensor([1], ms.int32)
>>> saliency = occlusion(input_x, label)
>>> print(saliency.shape)
(1, 1, 32, 32)
"""
def __init__(self, network, activation_fn, perturbation_per_eval=32):

2
mindspore/explainer/explanation/_attribution/_perturbation/rise.py
View File

@ -74,10 +74,12 @@ class RISE(PerturbationAttribution):
>>> targets = 5
>>> saliency = rise(inputs, targets)
>>> print(saliency.shape)
(2, 1, 32, 32)
>>> # `targets` can also be a 2D tensor
>>> targets = ms.Tensor([[5], [1]], ms.int32)
>>> saliency = rise(inputs, targets)
>>> print(saliency.shape)
(2, 1, 32, 32)
"""
def __init__(self,

21
mindspore/explainer/explanation/_counterfactual/hierarchical_occlusion.py
View File

@ -379,27 +379,6 @@ class Searcher:
strides (Union(list[int], optional): Stride of layers, None means by auto calcuation.
threshold (float): Threshold network output value of the target class.
by_masking (bool): Whether it is masking mode.
Examples:
>>> from mindspore import nn
>>> from mindspore.explainer.explanation._counterfactual.hierarchical_occlusion import Searcher, EditStep
>>>
>>> from user_defined import load_network, load_sample_image
>>>
>>>
>>> network = nn.SequentialCell([load_network(), nn.Sigmoid()])
>>>
>>> # single image in CHW or NCHW(N=1) numpy.ndarray tensor, typical dimension is 224x224
>>> image = load_sample_image()
>>> # target class index
>>> class_idx = 5
>>>
>>> # by default, maximum 3 search layers, auto calculate window sizes and strides
>>> searcher = Searcher(network)
>>>
>>> edit_tree, layer_outputs = searcher.search(image, class_idx)
>>> # get the outcome image of the deepest layer in CHW(or NCHW(N=1) if input image is NCHW) format
>>> outcome = EditStep.apply(image, searcher.compiled_mask, edit_tree.leaf_steps)
"""
def __init__(self,