Regression Task Scoring about tf-keras-vis

[keisen]

@Lswhiteh, I'm sorry for the lack of information.
InactiveScore is the function to inactivate the model output by multiplying by zero. (For example: #14)
tf-keras-vis doesn't have the score class for Regression task, so please refer to the following.

For purposes of brevity, I assume that the shape of your model's output is (samples, 1).
And, in Regression task, we need to consider how what you want to visualize contributes to the model output,
so suppose that you are interested in one (or more) of the following:

• Increase the output value
• Decrease the output value
• Maintain the output value at ...

(Because you've attempted to use InactiveScore, you're probably interested in Decrease the output value, right.)

The score functions you need will be one (or more) of the following:

def score_when_increase(output):
    return output[:, 0]

def score_when_decrease(output):
    return -1.0 * output[:, 0]

def score_when_maintain(output):
    # If you want to visualize the region of input that contributes to maintain the output at 0.0
    return tf.math.abs(1.0 / (output[:, 0] + tf.keras.backend.epsilon()))

For example, if you want to visualize the region of input that contributes the increase output, the usage is:

saliency_maps = saliency(score_when_increase, X)

If you have any question or any problem, please feel free to ask us.
Thanks!

[Lswhiteh]

This clarified quite a bit for me, thanks for the help!