Home

Awesome

Saliency Library

Updates

๐Ÿ”ดย ย  Now framework-agnostic! (Example core notebook) ย ๐Ÿ”ด

๐Ÿ”—ย ย  For further explanation of the methods and more examples of the resulting maps, see our Github Pages website ย ๐Ÿ”—

If upgrading from an older version, update old imports to import saliency.tf1 as saliency. We provide wrappers to make the framework-agnostic version compatible with TF1 models. (Example TF1 notebook)

๐Ÿ”ดย ย  Added Performance Information Curve (PIC) - a human independent metric for evaluating the quality of saliency methods. (Example notebook) ย ๐Ÿ”ด

Saliency Methods

This repository contains code for the following saliency techniques:

*Developed by PAIR.

This list is by no means comprehensive. We are accepting pull requests to add new methods!

Evaluation of Saliency Methods

The repository provides an implementation of Performance Information Curve (PIC) - a human independent metric for evaluating the quality of saliency methods (paper, poster, code, notebook).

Download

# To install the core subpackage:
pip install saliency

# To install core and tf1 subpackages:
pip install saliency[tf1]

or for the development version:

git clone https://github.com/pair-code/saliency
cd saliency

Usage

The saliency library has two subpackages:

Core

Each saliency mask class extends from the CoreSaliency base class. This class contains the following methods:

The visualization module contains two methods for saliency visualization:

If the sign of the value given by the saliency mask is not important, then use VisualizeImageGrayscale, otherwise use VisualizeImageDiverging. See the SmoothGrad paper for more details on which visualization method to use.

call_model_function

call_model_function is how we pass inputs to a given model and receive the outputs necessary to compute saliency masks. The description of this method and expected output format is in the CoreSaliency description, as well as separately for each method.

Examples

This example iPython notebook showing these techniques is a good starting place.

Here is a condensed example of using IG+SmoothGrad with TensorFlow 2:

import saliency.core as saliency
import tensorflow as tf

...

# call_model_function construction here.
def call_model_function(x_value_batched, call_model_args, expected_keys):
	tape = tf.GradientTape()
	grads = np.array(tape.gradient(output_layer, images))
	return {saliency.INPUT_OUTPUT_GRADIENTS: grads}

...

# Load data.
image = GetImagePNG(...)

# Compute IG+SmoothGrad.
ig_saliency = saliency.IntegratedGradients()
smoothgrad_ig = ig_saliency.GetSmoothedMask(image, 
											call_model_function, 
                                            call_model_args=None)

# Compute a 2D tensor for visualization.
grayscale_visualization = saliency.VisualizeImageGrayscale(
    smoothgrad_ig)

TF1

Each saliency mask class extends from the TF1Saliency base class. This class contains the following methods:

The visualization module contains two visualization methods:

If the sign of the value given by the saliency mask is not important, then use VisualizeImageGrayscale, otherwise use VisualizeImageDiverging. See the SmoothGrad paper for more details on which visualization method to use.

Examples

This example iPython notebook shows these techniques is a good starting place.

Another example of using GuidedBackprop with SmoothGrad from TensorFlow:

from saliency.tf1 import GuidedBackprop
from saliency.tf1 import VisualizeImageGrayscale
import tensorflow.compat.v1 as tf

...
# Tensorflow graph construction here.
y = logits[5]
x = tf.placeholder(...)
...

# Compute guided backprop.
# NOTE: This creates another graph that gets cached, try to avoid creating many
# of these.
guided_backprop_saliency = GuidedBackprop(graph, session, y, x)

...
# Load data.
image = GetImagePNG(...)
...

smoothgrad_guided_backprop =
    guided_backprop_saliency.GetMask(image, feed_dict={...})

# Compute a 2D tensor for visualization.
grayscale_visualization = visualization.VisualizeImageGrayscale(
    smoothgrad_guided_backprop)

Conclusion/Disclaimer

If you have any questions or suggestions for improvements to this library, please contact the owners of the PAIR-code/saliency repository.

This is not an official Google product.