PatternAttribution for iNNvestigate 2.0 version

[moritzaugustin]

The great method "PatternAttribution" was available in the previous iNNvestigate version (for tensorflow 1) and is not available anymore for the current version for tensorflow 2.

I wonder whether it is planned to implement the method again and if so when it will be available? :-)

In the README.md it is stated: pattern.net: PatternNet estimates the input signal of the output neuron. (Note: not available in iNNvestigate 2.0)

[adrhill]

Hi Moritz,

I currently don't have the bandwidth to implement "new" features, but I'd welcome contributions.
To check the correctness of a new implementation, data for reference tests can be generated via https://github.com/adrhill/test-data-innvestigate.

I'll leave this issue open as a feature request.

Note: For users that have the option to use TensorFlow 1, PatternAttribution and PatternNet are still available by installing iNNvestigate 1.0.8..

[mg97tud]

I am using tensorflow-directml 1.15 (to use my AMD GPU) and I can use iNNvestigate 2.0 without problems. But when I want to use iNNvestigate 1.0.8.3. I get the Error "module 'tensorflow._api.v1.compat.v2' has no attribute 'internal'". Is this, because
iNNvestigate 1.0.8.3 was written and tested for tensorflow 1.12? I sadly cant downgrade from 1.15.

[adrhill]

Yes exactly, iNNvestigate 2.0.0 is a breaking release that switched from TF1 to TF2, dropping TF1 compatibility.
I'm not familiar with tensorflow-directml, but it would have to be compatible with TF1 for iNNvestigate 1.0.8 to work.

[mg97tud]

Thats what bugging me. Tensorflow 1.15 is the latest Tensorflow 1 Version, right? tensorflow-directml is build on TF 1.15.
I can use innvestigate 2.0 with my 1.15 Tensorflow, but not innvestigate 1.0.8

[adrhill]

The latest stable release of TensorFlow by Google is 2.9.1. The major version number is what people refer to when they talk about TF1 and TF2.

The latest release of tensorflow-directml is 1.15.7. tensorflow-directml is not the "official" TensorFlow, but a fork by Microsoft. Since iNNvestigate builds upon Google's TensorFlow, our tests and CI don't guarantee any functionality for forks.

Since I'm not familiar with tensorflow-directml, I'm not able to tell you how compatible it is with packages like iNNvestigate that use internals of Google's TensorFlow 1 and 2. Maybe the tensorflow-directml FAQ have an answer to your question.

[adrhill]

In case it helps: previous releases of iNNvestigate (1.0.8, 1.0.9) used Keras 2.2.4 and TensorFlow 1.12:

innvestigate/README.md

Line 38 in e76ec2d

o(Currently only the Tensorflow backend is supported. We test with Python 3.6, Tensorflow 1.12 and Cuda 9.x.):

innvestigate/setup.py

Line 11 in e76ec2d

"keras==2.2.4",

We then jumped all TensorFlow versions between 1.12 and ^2.6 for iNNvestigate 2.0.