Vijay Arya

@Lawrence-Krukrubo I hope you are following these steps. Then you should be able to use CEMexplainer. (base)$ `conda create --name aix360 python=3.6` (base)$ `conda activate aix360` (aix360)$ `git clone https://github.com/Trusted-AI/AIX360`...

@Lawrence-Krukrubo when do you get this error. Which notebook you are trying to run and the code that gives you the error. Also some info on the system you are...

@Lawrence-Krukrubo If you are getting `ModuleNotFoundError: No module named 'tensorflow.contrib` error, then it means you have a higher version of tensorflow being used somewhere and you are running code that...

nn.contrastive is a black box explainer, type of model does not matter. CEM is a white box explainer, its code looks inside the model, so model's TF version would matter....

The MNIST example is also run as a test for CEM from here: https://github.com/Trusted-AI/AIX360/blob/master/tests/contrastive/test_CEM.py You can see the test run results here for windows, mac, and linux: https://github.com/Trusted-AI/AIX360/actions/runs/5375947859/jobs/9752428343

@Tomcli pull #174 addresses this.

@elukey You can install each algorithm separately with different dependencies now, so tf version should not be an issue. Most algorithms are compatible with higher versions of python. Please see...