Xai base
XAImethod_Base
¤
Bases: ABC
An abstract base class for a XAI Method class.
Normally, this class is used internally in the xai_decoder function in the AUCMEDI XAI module.
This class provides functionality for running the compute_heatmap function, which computes a heatmap for an image with a model.
Create a custom XAImethod
from aucmedi.xai.methods.xai_base import XAImethod_Base
class My_custom_XAImethod(XAImethod_Base):
def __init__(self, model, layerName=None):
pass
def compute_heatmap(self, image, class_index, eps=1e-8):
pass
Required Functions
Function | Description |
---|---|
__init__() |
Object creation function. |
compute_heatmap() |
Application of the XAI Method on an image. |
Source code in aucmedi/xai/methods/xai_base.py
28 29 30 31 32 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 |
|
__init__(model, layerName=None)
abstractmethod
¤
Initialization function for creating a XAI Method object.
__init__(model, layerName=None)
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/xai_base.py
58 59 60 61 62 63 64 65 66 67 68 69 |
|
compute_heatmap(image, class_index, eps=1e-08)
¤
Core function for computing the XAI 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 should be 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 XAI heatmap for provided image. |
Source code in aucmedi/xai/methods/xai_base.py
74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
|