Data shape for saliency map about tf-keras-vis

[keisen]

Hi @Priende , thank you for enjoying tf-keras-vis.

I recommend you to use keepdims option in Saliency.
In default, Saliency work for image data, so channels dimension in input data is eliminate.
When keepdims is True, Saliency will work to reach your goal.

tf-keras-vis/tf_keras_vis/saliency.py

Line 15 in 0448556

keepdims=False,

If I instead first transpose the input shape to (3, 33, 128, 1) to match the shape of the image data in the attentions example, I get the following error:

Although I don't know specific cause, It seems the error is NOT caused by tf-keras-vis.

[Priende]

Perfect, thank you!