Skip to content

Latest commit

 

History

History
64 lines (45 loc) · 2.4 KB

README-CONFIGURATION.md

File metadata and controls

64 lines (45 loc) · 2.4 KB

⚙️ Configure ⚙️

The tool can be configured using the files:

config/config_dirs.py
This file defines the location of the inputs and the outputs of the tool.
config/config_const.py
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.

config/config_general.py
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.

config/config_heatmaps.py
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.

config/config_featuremaps.py
This fle defines the configuration for the featuremaps.

NUM_CELLS: The size of the featuremaps.

BITMAP_THRESHOLD: COMPLETE

ORIENTATION_THRESHOLD: COMPLETE

FEATUREMAPS_CLUSTERS_MODE: The clustering technique to use on the featuremaps [ORIGINAL, REDUCED].