_model_utils

Module Contents

Functions

preprocess_function(image)

For LIME: we divided the input data by 256 for the model (binary mnist) and LIME needs RGB values.

fill_segmentation(values, segmentation)

For KernelSHAP: fill each pixel with SHAP values.

load_model(file)

load_labels(file)

_model_utils.preprocess_function(image)[source]

For LIME: we divided the input data by 256 for the model (binary mnist) and LIME needs RGB values.

_model_utils.fill_segmentation(values, segmentation)[source]

For KernelSHAP: fill each pixel with SHAP values.

_model_utils.load_model(file)[source]
_model_utils.load_labels(file)[source]