The tool can be configured using the files:
- This file defines the location of the inputs and the outputs of the tool.
-
Ths file defines configurations for some constants used by the tool.
EXPECTED_LABEL
: The label to use to filter the data for the experiment.MAX_LABELS
,MAX_SAMPLES
: Respectively the maximum number of rows and columns to use when exporting the sample images for the clusters.IMG_SIZE
: The size of the images in the dataset.NUM_CLASSES
: The number of classes for the data labels.GRID_SIZE
: The size of the grid used for the sufficiency evaluation. -
Ths file defines configurations common to both the heatmaps and the featuremaps.
CLUSTERS_SORT_METRIC
: The preference for the clusters when sampling them to show some of their images. If no sorting is provided, the tool draw a random sample.CLUSTER_SIMILARITY_METRIC
: The similarity metric to use when comparing different clusters. -
This fle defines the configuration for the heatmaps.
HEATMAPS_PROCESS_MODE
: The processing mode to use when generating the heatmaps [LocalLatentMode
,GlobalLatentMode
].EXPLAINERS
: The list of explainers to use when generating the contributions.DIMENSIONALITY_REDUCTION_TECHNIQUES
: The dimensionality reduction techniques to use to project the contributions in the two-dimensional latent space. The tool will experiment with the different techniques and choose the best configuration according to the silhouette score of the corresponding clusters.CLUSTERING_TECHNIQUE
: The clustering technique to use when grouping the contributions.ITERATIONS
: The number of iterations to use when running the experiment. -
This fle defines the configuration for the featuremaps.
NUM_CELLS
: The size of the featuremaps.BITMAP_THRESHOLD
: COMPLETEORIENTATION_THRESHOLD
: COMPLETEFEATUREMAPS_CLUSTERS_MODE
: The clustering technique to use on the featuremaps [ORIGINAL
,REDUCED
].
config/config_dirs.py
config/config_const.py
config/config_general.py
config/config_heatmaps.py
config/config_featuremaps.py