Why the guided gradients?

[ISipi]

Hi, could you explain the use of the guided gradients (below) with respect to the Selvaraju et al. 2019 paper? Do these guided gradients refer to the Guided Backpropagation part? I also don't see you using ReLU at any point?

# compute the guided gradients
castConvOutputs = tf.cast(convOutputs > 0, "float32")
castGrads = tf.cast(grads > 0, "float32")
guidedGrads = castConvOutputs * castGrads * grads