Hi, dalex will work with any model for which you can pass a predict_function to dx.Explainer. This function inputs a model with data as np.ndarray pd.DataFrame and returns a 1-dimensional np.ndarray with model predictions. Examples of such predict functions: https://github.com/ModelOriented/DALEX/blob/master/python/dalex/dalex/_explainer/yhat.py

Notably, for tensorflow, it looks like this:

def yhat_tf_regression(m, d):
    return m.predict(np.array(d), verbose=0).reshape(-1, )

def yhat_tf_classification(m, d):
    return m.predict(np.array(d), verbose=0)[:, 1]

Thank you very much! I will test it with PyTorch.

reopen if needed