Bases: XAImethod_Base
XAI Method for Guided Grad-CAM.
Normally, this class is used internally in the aucmedi.xai.decoder.xai_decoder in the AUCMEDI XAI module.
Reference - Implementation
Author: Swapnil Ahlawat
Date: Jul 06, 2020
https://github.com/swapnil-ahlawat/Guided-GradCAM-Keras
Reference - Publication #1
Jost Tobias Springenberg, Alexey Dosovitskiy, Thomas Brox, Martin Riedmiller. 21 Dec 2014.
Striving for Simplicity: The All Convolutional Net.
https://arxiv.org/abs/1412.6806
Reference - Publication #2
Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra. 7 Oct 2016.
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization.
https://arxiv.org/abs/1610.02391
This class provides functionality for running the compute_heatmap function,
which computes a Guided Grad-CAM heatmap for an image with a model.
Source code in aucmedi/xai/methods/gradcam_guided.py
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103 | class GuidedGradCAM(XAImethod_Base):
""" XAI Method for Guided Grad-CAM.
Normally, this class is used internally in the [aucmedi.xai.decoder.xai_decoder][] in the AUCMEDI XAI module.
??? abstract "Reference - Implementation"
Author: Swapnil Ahlawat <br>
Date: Jul 06, 2020 <br>
[https://github.com/swapnil-ahlawat/Guided-GradCAM-Keras](https://github.com/swapnil-ahlawat/Guided-GradCAM-Keras) <br>
??? abstract "Reference - Publication #1"
Jost Tobias Springenberg, Alexey Dosovitskiy, Thomas Brox, Martin Riedmiller. 21 Dec 2014.
Striving for Simplicity: The All Convolutional Net.
<br>
[https://arxiv.org/abs/1412.6806](https://arxiv.org/abs/1412.6806)
??? abstract "Reference - Publication #2"
Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra. 7 Oct 2016.
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization.
<br>
[https://arxiv.org/abs/1610.02391](https://arxiv.org/abs/1610.02391)
This class provides functionality for running the compute_heatmap function,
which computes a Guided Grad-CAM heatmap for an image with a model.
"""
def __init__(self, model, layerName=None):
""" Initialization function for creating a Guided Grad-CAM as XAI Method object.
Args:
model (keras.model): Keras model object.
layerName (str): Layer name of the convolutional layer for heatmap computation.
"""
# Initialize XAI methods
self.bp = GuidedBackpropagation(model, layerName)
self.gc = GradCAM(model, layerName)
#---------------------------------------------#
# Heatmap Computation #
#---------------------------------------------#
def compute_heatmap(self, image, class_index, eps=1e-8):
""" Core function for computing the Guided Grad-CAM heatmap for a provided image and for specific classification outcome.
???+ attention
Be aware that the image has to be provided in batch format.
Args:
image (numpy.ndarray): Image matrix encoded as NumPy Array (provided as one-element batch).
class_index (int): Classification index for which the heatmap should be computed.
eps (float): Epsilon for rounding.
The returned heatmap is encoded within a range of [0,1]
???+ attention
The shape of the returned heatmap is 2D -> batch and channel axis will be removed.
Returns:
heatmap (numpy.ndarray): Computed Guided Grad-CAM for provided image.
"""
# Compute Guided Backpropagation
hm_bp = self.bp.compute_heatmap(image, class_index, eps)
# Compute Grad-CAM
hm_gc = self.gc.compute_heatmap(image, class_index, eps)
hm_gc = Resize(shape=image.shape[1:-1]).transform(hm_gc)
# Combine both XAI methods
heatmap = hm_bp * hm_gc
# Intensity normalization to [0,1]
numer = heatmap - np.min(heatmap)
denom = (heatmap.max() - heatmap.min()) + eps
heatmap = numer / denom
# Return the resulting heatmap
return heatmap
|
__init__(model, layerName=None)
Initialization function for creating a Guided Grad-CAM as XAI Method object.
Parameters:
| Name |
Type |
Description |
Default |
model |
keras.model
|
Keras model object. |
required
|
layerName |
str
|
Layer name of the convolutional layer for heatmap computation. |
None
|
Source code in aucmedi/xai/methods/gradcam_guided.py
58
59
60
61
62
63
64
65
66
67 | def __init__(self, model, layerName=None):
""" Initialization function for creating a Guided Grad-CAM as XAI Method object.
Args:
model (keras.model): Keras model object.
layerName (str): Layer name of the convolutional layer for heatmap computation.
"""
# Initialize XAI methods
self.bp = GuidedBackpropagation(model, layerName)
self.gc = GradCAM(model, layerName)
|
compute_heatmap(image, class_index, eps=1e-08)
Core function for computing the Guided Grad-CAM heatmap for a provided image and for specific classification outcome.
Attention
Be aware that the image has to be provided in batch format.
Parameters:
| Name |
Type |
Description |
Default |
image |
numpy.ndarray
|
Image matrix encoded as NumPy Array (provided as one-element batch). |
required
|
class_index |
int
|
Classification index for which the heatmap should be computed. |
required
|
eps |
float
|
Epsilon for rounding. |
1e-08
|
The returned heatmap is encoded within a range of [0,1]
Attention
The shape of the returned heatmap is 2D -> batch and channel axis will be removed.
Returns:
| Name | Type |
Description |
heatmap |
numpy.ndarray
|
Computed Guided Grad-CAM for provided image. |
Source code in aucmedi/xai/methods/gradcam_guided.py
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103 | def compute_heatmap(self, image, class_index, eps=1e-8):
""" Core function for computing the Guided Grad-CAM heatmap for a provided image and for specific classification outcome.
???+ attention
Be aware that the image has to be provided in batch format.
Args:
image (numpy.ndarray): Image matrix encoded as NumPy Array (provided as one-element batch).
class_index (int): Classification index for which the heatmap should be computed.
eps (float): Epsilon for rounding.
The returned heatmap is encoded within a range of [0,1]
???+ attention
The shape of the returned heatmap is 2D -> batch and channel axis will be removed.
Returns:
heatmap (numpy.ndarray): Computed Guided Grad-CAM for provided image.
"""
# Compute Guided Backpropagation
hm_bp = self.bp.compute_heatmap(image, class_index, eps)
# Compute Grad-CAM
hm_gc = self.gc.compute_heatmap(image, class_index, eps)
hm_gc = Resize(shape=image.shape[1:-1]).transform(hm_gc)
# Combine both XAI methods
heatmap = hm_bp * hm_gc
# Intensity normalization to [0,1]
numer = heatmap - np.min(heatmap)
denom = (heatmap.max() - heatmap.min()) + eps
heatmap = numer / denom
# Return the resulting heatmap
return heatmap
|