classifier = SupervisedDBNClassification(hidden_layers_structure=[100, 100, 100],
learning_rate_rbm=0.05,
learning_rate=0.1,
n_epochs_rbm=10,
n_iter_backprop=100,
batch_size=20, # 32
activation_function='relu',
dropout_p=0.2)
model = classifier.fit(X_train, Y_train)
explainer = shap.DeepExplainer(model, X_train)
https://github.com/albertbup/deep-belief-network
SupervisedDBNClassification来自此链接