SHAP explainer identifies wrong framework

Question

I want to use the SHAP-DeepInterpeter on the Braindecode Shallow_FBCSP-Model which is based on pytorch.

The training and testing works perfectly fine on the model but when I try to pass the model to SHAP it somehow recognize the tensorflow framework and not the pytorch framework.

For Code:

e = shap.DeepExplainer(model, background)

I get following Error:

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
<ipython-input-63-9c7a102b5020> in <module>
     32 print(type(model))
     33 
---> 34 e = shap.DeepExplainer(model, background)
     35 #shap_values = e.shap_values(test_images)

~\miniconda3\envs\braindecode\lib\site-packages\shap\explainers\_deep\__init__.py in __init__(self, model, data, session, learning_phase_flags)
     82 
     83         if framework == 'tensorflow':
---> 84             self.explainer = TFDeep(model, data, session, learning_phase_flags)
     85         elif framework == 'pytorch':
     86             self.explainer = PyTorchDeep(model, data)

~\miniconda3\envs\braindecode\lib\site-packages\shap\explainers\_deep\deep_tf.py in __init__(self, model, data, session, learning_phase_flags)
     76         global tf, tf_ops, tf_backprop, tf_execute, tf_gradients_impl
     77         if tf is None:
---> 78             from tensorflow.python.framework import ops as tf_ops # pylint: disable=E0611
     79             from tensorflow.python.ops import gradients_impl as tf_gradients_impl # pylint: disable=E0611
     80             from tensorflow.python.eager import backprop as tf_backprop

ModuleNotFoundError: No module named 'tensorflow'

As said my Model has the type

<class 'braindecode.models.shallow_fbcsp.ShallowFBCSPNet'>

Has someone an idea what I missed ?

Thanks in advance!