This notebook is designed to demonstrate (and so document) how to use the
from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input import json import shap import tensorflow as tf # load pre-trained model and choose two images to explain model = ResNet50(weights='imagenet') def f(X): tmp = X.copy() preprocess_input(tmp) return model(tmp) X, y = shap.datasets.imagenet50() # load the ImageNet class names as a vectorized mapping function from ids to names url = "https://s3.amazonaws.com/deep-learning-models/image-models/imagenet_class_index.json" with open(shap.datasets.cache(url)) as file: class_names = [v for v in json.load(file).values()] # define a masker that is used to mask out partitions of the input image, this one uses a blurred background masker = shap.maskers.Image("inpaint_telea", X.shape) # By default the Partition explainer is used for all partition explainer explainer = shap.Explainer(f, masker, output_names=class_names) # here we use 500 evaluations of the underlying model to estimate the SHAP values shap_values = explainer(X[1:3], max_evals=500, batch_size=50, outputs=shap.Explanation.argsort.flip[:1]) shap.image_plot(shap_values)
explainers.Partition is still in an alpha state, so use with caution...
Partition explainer: 3it [00:18, 6.10s/it]
Have an idea for more helpful examples? Pull requests that add to this documentation notebook are encouraged!